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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Subject
    -0.07
    本轮
    -0.07
     revised
    -0.07
     mutil
    -0.07
     infer
    -0.06
     Auditor
    -0.06
    VER
    -0.06
     quiz
    -0.06
     분
    -0.06
    /********************************************************************************
    -0.06
    POSITIVE LOGITS
    Ids
    0.07
    곤
    0.07
     incredibly
    0.06
    arp
    0.06
    所有的
    0.06
    ilde
    0.06
    Match
    0.06
    ean
    0.06
    使って
    0.06
    aco
    0.06
    Act Density 0.027%

    No Known Activations