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

    Neuronpedia

    INDEX
    Explanations

    Code, URLs, special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hips
    -0.27
    éĢļçĶ¨
    -0.26
    agal
    -0.25
    ison
    -0.25
    -Pack
    -0.24
    legen
    -0.24
    åĽ¢è´Ń
    -0.24
    ago
    -0.23
    ItemAt
    -0.23
    deaux
    -0.23
    POSITIVE LOGITS
     wes
    0.27
    ľëł¥
    0.27
    ieri
    0.27
    beer
    0.25
    olvers
    0.25
    oris
    0.25
    sert
    0.25
    |[
    0.25
    æľ¬æĬ¥è®¯
    0.24
    Lex
    0.24
    Act Density 0.330%

    No Known Activations