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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    如意
    -0.07
     entropy
    -0.07
    ジェ
    -0.06
     TRANS
    -0.06
    協
    -0.06
     TELE
    -0.06
    People
    -0.06
    电动
    -0.06
     Mozart
    -0.06
     Dynam
    -0.06
    POSITIVE LOGITS
     vals
    0.06
    תחת
    0.06
    _via
    0.06
    ahan
    0.06
    _vars
    0.06
    撸
    0.06
    (Buffer
    0.06
     tattoo
    0.06
    _SETTING
    0.06
    难忘
    0.06
    Act Density 0.001%

    No Known Activations