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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abelle
    -0.07
    ClassNotFoundException
    -0.07
    銀行
    -0.07
     Bell
    -0.07
     rectangle
    -0.07
     hail
    -0.07
     BAR
    -0.07
    /r
    -0.07
    _INLINE
    -0.07
     farewell
    -0.07
    POSITIVE LOGITS
     most
    0.08
     guit
    0.08
     the
    0.07
     반드
    0.06
     kitabı
    0.06
    𦒍
    0.06
    rist
    0.06
    ு
    0.06
    Finite
    0.06
    �
    0.06
    Act Density 0.064%

    No Known Activations