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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNIVERS
    -0.06
    obi
    -0.06
    _evt
    -0.06
     Obr
    -0.06
    eyh
    -0.06
     operating
    -0.06
    material
    -0.06
     BS
    -0.06
    zn
    -0.06
    +"</
    -0.06
    POSITIVE LOGITS
     hardcoded
    0.06
    always
    0.06
     лим
    0.06
     palavra
    0.06
    {(
    0.06
     hardcore
    0.06
     컴
    0.06
     penetrate
    0.06
     urg
    0.06
    auen
    0.06
    Act Density 0.007%

    No Known Activations