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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _goto
    -0.07
    (src
    -0.07
     Fem
    -0.07
     kicking
    -0.06
    نتاج
    -0.06
     knull
    -0.06
     insensitive
    -0.06
    وة
    -0.06
     axe
    -0.06
    grow
    -0.06
    POSITIVE LOGITS
     there
    0.07
     complaint
    0.07
     Sı
    0.06
     Complaint
    0.06
    Still
    0.06
    .sock
    0.06
     boasts
    0.06
     still
    0.06
    -year
    0.06
    .There
    0.06
    Act Density 0.013%

    No Known Activations