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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or items being discussed

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

    "This" or "that" followed by a question or statement

    np_acts-logits-general · gemini-2.0-flash

    this that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itulah
    -0.53
    '){
    -0.51
    seamnă
    -0.49
     %).
    -0.49
     riuscito
    -0.48
    Портал
    -0.47
    ']));
    -0.46
     duquel
    -0.46
     resembles
    -0.45
     precedes
    -0.45
    POSITIVE LOGITS
     stuff
    0.79
     insuffisamment
    0.69
     bezeichneter
    0.68
     particular
    0.66
     situation
    0.65
     Winaray
    0.65
    expandindo
    0.64
     चीज़ों
    0.63
    particular
    0.63
    principalTable
    0.63
    Act Density 0.235%

    No Known Activations