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

    Neuronpedia

    INDEX
    Explanations

    semicolon/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弗
    -0.07
     Regular
    -0.07
     inadvertently
    -0.07
    _instruction
    -0.06
     sinus
    -0.06
    .Keyboard
    -0.06
    _RG
    -0.06
     Vš
    -0.06
    放
    -0.06
     Kum
    -0.06
    POSITIVE LOGITS
     injuring
    0.06
    mina
    0.06
    itelist
    0.06
    atisfied
    0.06
     holy
    0.06
    网址
    0.06
    ESTAMP
    0.06
     brat
    0.05
    .usage
    0.05
    луата
    0.05
    Act Density 0.002%

    No Known Activations