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

    Neuronpedia

    INDEX
    Explanations

    instances of personal identification and documentation

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

    identity verification documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     msglen
    -0.42
    izr
    -0.40
    odend
    -0.39
     кӀ
    -0.35
    Stones
    -0.31
     PLE
    -0.31
     hat
    -0.31
    Wrk
    -0.31
    HasColumnType
    -0.30
     kek
    -0.30
    POSITIVE LOGITS
    ✨:
    0.56
     Umum
    0.50
    ViewFeatures
    0.50
    alakip
    0.50
     contigo
    0.49
    ñores
    0.49
     légal
    0.47
     esternos
    0.47
     autorytatywna
    0.47
     alér
    0.46
    Act Density 0.033%

    No Known Activations