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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to determination and importance

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

    "the" followed by a positive word

    np_acts-logits-general · gemini-2.0-flash

    way, focus, or thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faptul
    -0.72
     propres
    -0.56
     egne
    -0.54
    httphttps
    -0.54
    OGND
    -0.51
    queles
    -0.51
     scatola
    -0.50
     ferdig
    -0.50
     noodzake
    -0.49
     resourceCulture
    -0.48
    POSITIVE LOGITS
     deal
    1.15
     DEAL
    0.83
    deal
    0.77
     Deal
    0.76
     answer
    0.75
     plan
    0.71
     route
    0.71
     gist
    0.70
     ticket
    0.70
     focus
    0.68
    Act Density 0.216%

    No Known Activations