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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Code, packages, obtaining information, analysis

    np_acts-logits-general · gemini-2.0-flash

    bind, analyze, person, been, by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دیکھیے
    -0.56
    Enumerator
    -0.54
    السكان
    -0.53
    یده
    -0.52
     Insee
    -0.51
    hnout
    -0.50
     cataract
    -0.49
     légales
    -0.49
    schlag
    -0.48
    Superview
    -0.48
    POSITIVE LOGITS
    bind
    0.73
     Bind
    0.68
     bind
    0.66
     binds
    0.64
    BagConstraints
    0.63
     لينك
    0.63
     صوتيه
    0.62
    wiſe
    0.60
    ſelf
    0.58
     binders
    0.58
    Act Density 0.005%

    No Known Activations