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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    640
    -0.08
    Associate
    -0.07
     Aud
    -0.07
     온
    -0.07
    На
    -0.06
     Cat
    -0.06
     lineman
    -0.06
     円
    -0.06
    نگ
    -0.06
    /plugins
    -0.06
    POSITIVE LOGITS
    /'.
    0.06
     Gibson
    0.06
    .visibility
    0.06
    DONE
    0.06
    grave
    0.05
     بالن
    0.05
    /;↵
    0.05
     swingers
    0.05
     Receive
    0.05
    <TSource
    0.05
    Act Density 0.122%

    No Known Activations