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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    去了
    -0.07
    47
    -0.07
     thường
    -0.06
    /cop
    -0.06
     bringen
    -0.06
    관리
    -0.06
     whore
    -0.06
     cứ
    -0.06
     killer
    -0.06
    寒
    -0.06
    POSITIVE LOGITS
     Gal
    0.07
     querying
    0.07
    _SPEC
    0.07
    DEFINED
    0.07
     blatantly
    0.07
    ALT
    0.06
    ิศาสตร
    0.06
    Gil
    0.06
     Spicer
    0.06
    _CH
    0.06
    Act Density 0.255%

    No Known Activations