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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attempting
    -0.08
     equally
    -0.08
     uu
    -0.08
     ipAddress
    -0.08
    $/,
    -0.07
     Manson
    -0.07
    逮捕
    -0.07
     ?,
    -0.07
    ;,
    -0.07
    堋
    -0.07
    POSITIVE LOGITS
    (/*
    0.07
     Tablet
    0.07
    nesia
    0.07
    amespace
    0.07
     Realty
    0.07
     undergrad
    0.06
    אק
    0.06
     tranny
    0.06
    랕
    0.06
     Singleton
    0.06
    Act Density 0.021%

    No Known Activations