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

    Neuronpedia

    INDEX
    Explanations

    vegetables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    刻
    -0.08
    NullException
    -0.08
     text
    -0.07
    licos
    -0.07
    dfs
    -0.07
    盾
    -0.07
    慢慢
    -0.07
     ND
    -0.06
     dhe
    -0.06
    lli
    -0.06
    POSITIVE LOGITS
     homic
    0.07
    _SER
    0.07
    isFunction
    0.07
    ⚙
    0.07
    /mock
    0.07
     рол
    0.07
    (comb
    0.06
    готов
    0.06
    せい
    0.06
    อำนวยความ
    0.06
    Act Density 0.046%

    No Known Activations