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

    Neuronpedia

    INDEX
    Explanations

    the be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ẫu
    -0.08
    _Pos
    -0.07
    .kode
    -0.07
    ­s
    -0.07
     cyclist
    -0.07
     đời
    -0.06
     nửa
    -0.06
     소개
    -0.06
    .nome
    -0.06
    Between
    -0.06
    POSITIVE LOGITS
     fined
    0.06
     fortunate
    0.06
    ival
    0.06
    éc
    0.06
     Ли
    0.06
    ISBN
    0.06
    inq
    0.06
    ава
    0.06
    	Check
    0.06
    (current
    0.06
    Act Density 0.032%

    No Known Activations