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

    Neuronpedia

    INDEX
    Explanations

    .pyplot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (original
    -0.07
     Gutenberg
    -0.07
    bet
    -0.06
    amines
    -0.06
     particul
    -0.06
    вал
    -0.06
    xis
    -0.06
     �
    -0.06
    Destination
    -0.06
    (normal
    -0.06
    POSITIVE LOGITS
     rights
    0.07
     [...
    0.07
    �
    0.06
    動
    0.06
    itespace
    0.06
    endment
    0.06
    USA
    0.06
    TW
    0.06
    (console
    0.06
     pena
    0.06
    Act Density 0.001%

    No Known Activations