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

    Neuronpedia

    INDEX
    Explanations

    Code classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Band
    -0.07
    BEST
    -0.06
     kötü
    -0.06
    ょう
    -0.06
    >f
    -0.05
    gallery
    -0.05
    apes
    -0.05
     rolls
    -0.05
    .viewmodel
    -0.05
     Weekly
    -0.05
    POSITIVE LOGITS
    شور
    0.08
     -.
    0.07
    φων
    0.07
     immune
    0.07
    �
    0.07
    Question
    0.07
    forcer
    0.07
    ัจจ
    0.06
    cla
    0.06
    صول
    0.06
    Act Density 0.013%

    No Known Activations