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

    Neuronpedia

    INDEX
    Explanations

    utf-8 encoding and decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inserted
    0.59
     ,[
    0.49
    adore
    0.46
    ים
    0.46
    inserted
    0.46
     microfilm
    0.46
    adanam
    0.45
    pushButton
    0.45
    LockButton
    0.45
     abbreviated
    0.44
    POSITIVE LOGITS
    Tcp
    0.45
     Unwrap
    0.43
    提到
    0.42
     problème
    0.42
    TRS
    0.41
     perlu
    0.41
    ccos
    0.41
    rectionType
    0.41
    तालों
    0.40
     لحاظ
    0.40
    Act Density 0.022%

    No Known Activations