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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffi
    -0.08
     trilogy
    -0.07
    制剂
    -0.07
    ff
    -0.06
    因子
    -0.06
    瘅
    -0.06
     garner
    -0.06
     ,$
    -0.06
    🎲
    -0.06
    共生
    -0.06
    POSITIVE LOGITS
    �
    0.07
    _REFERER
    0.07
     Henry
    0.07
    -destruct
    0.07
    偷
    0.07
    craper
    0.07
    чит
    0.07
    ações
    0.07
    iri
    0.07
    �
    0.07
    Act Density 0.012%

    No Known Activations