Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to awareness and realization regarding social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "realize" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    realize the importance of existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     believed
    -0.56
    ništvo
    -0.54
    lnie
    -0.51
    celle
    -0.51
    Confirmed
    -0.51
    ardown
    -0.50
    Espèce
    -0.50
     confirmed
    -0.48
     verified
    -0.48
     investigated
    -0.47
    POSITIVE LOGITS
    esistenza
    0.84
     existence
    0.81
     enjeux
    0.78
    importanza
    0.76
    existence
    0.75
     שוליים
    0.74
    ագրություններ
    0.74
     importance
    0.73
    possibility
    0.71
    importance
    0.70
    Act Density 0.304%

    No Known Activations