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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EFR
    -0.07
    subtotal
    -0.06
    秒
    -0.06
    Hon
    -0.06
    _timestamp
    -0.06
    cher
    -0.06
    exercise
    -0.06
    ريب
    -0.06
    Junior
    -0.06
    By
    -0.06
    POSITIVE LOGITS
     mankind
    0.07
     affecting
    0.07
     ovšem
    0.07
     ακό
    0.07
     dreaded
    0.06
     bilir
    0.06
    /twitter
    0.06
     classic
    0.06
     profess
    0.06
     heroine
    0.06
    Act Density 0.045%

    No Known Activations