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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .compose
    -0.08
    ObjectContext
    -0.07
    Iraq
    -0.07
    (Android
    -0.07
    -trash
    -0.07
    (IC
    -0.07
    _PED
    -0.07
    .of
    -0.07
     "'",
    -0.07
    .World
    -0.07
    POSITIVE LOGITS
     Rihanna
    0.07
     paz
    0.07
    معايير
    0.07
     been
    0.07
    been
    0.06
    adesh
    0.06
    wait
    0.06
    frauen
    0.06
    โดน
    0.06
    �
    0.06
    Act Density 0.029%

    No Known Activations