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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ніби
    -0.07
    eb
    -0.07
    ulerAngles
    -0.06
     Ukrainian
    -0.06
     Cunningham
    -0.06
    ros
    -0.06
    MF
    -0.06
    ensors
    -0.06
     voluntarily
    -0.06
     UPLOAD
    -0.06
    POSITIVE LOGITS
    .openConnection
    0.06
    <decimal
    0.06
    istar
    0.06
     cigarette
    0.06
    _female
    0.06
     iterations
    0.06
     accumulation
    0.06
    istorical
    0.06
    aunch
    0.05
    astro
    0.05
    Act Density 0.112%

    No Known Activations