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

    Neuronpedia

    INDEX
    Explanations

    gibberish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    설
    -0.07
     �
    -0.06
     crate
    -0.06
    할
    -0.06
     说
    -0.06
    .states
    -0.06
    verter
    -0.06
    كرة
    -0.06
     ragazze
    -0.06
    .UNRELATED
    -0.06
    POSITIVE LOGITS
    Enumerable
    0.07
    xFA
    0.06
     Основ
    0.06
     छ
    0.06
    .Cos
    0.06
    _timeline
    0.06
     pagan
    0.06
     SMTP
    0.06
     disease
    0.06
    _MEMBERS
    0.06
    Act Density 0.028%

    No Known Activations