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

    Neuronpedia

    INDEX
    Explanations

    states and flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prey
    0.43
     разум
    0.43
    maxLength
    0.40
    かどうか
    0.39
    áci
    0.38
    (;
    0.38
     клиен
    0.37
    setVisibility
    0.37
    是否
    0.37
    MsgCallBack
    0.37
    POSITIVE LOGITS
    ビール
    0.38
    屓
    0.38
     Williamson
    0.37
    మై
    0.37
     realiz
    0.37
     terc
    0.37
     retardation
    0.37
    0.36
    テーブル
    0.36
     Roja
    0.36
    Act Density 0.019%

    No Known Activations