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

    Neuronpedia

    INDEX
    Explanations

    Vehicle history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certificates
    -0.07
    Tour
    -0.07
    _picker
    -0.07
     Warfare
    -0.06
    words
    -0.06
    Weak
    -0.06
     alphanumeric
    -0.06
    ();↵↵
    -0.06
    $info
    -0.06
    ملة
    -0.06
    POSITIVE LOGITS
     mj
    0.07
     cush
    0.07
    <!
    0.06
    ivr
    0.06
     Bij
    0.06
     emerged
    0.06
     Vij
    0.06
     东
    0.06
    tps
    0.06
    "/><
    0.06
    Act Density 0.185%

    No Known Activations