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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Explicit
    -0.07
    checked
    -0.07
     dwar
    -0.06
     kits
    -0.06
    вад
    -0.06
     présent
    -0.06
    uebas
    -0.06
    invalidate
    -0.06
     throat
    -0.06
    forgot
    -0.06
    POSITIVE LOGITS
     一
    0.07
     Satoshi
    0.07
     весь
    0.07
     والتي
    0.06
     ăn
    0.06
    _DI
    0.06
    .secret
    0.06
    ималь
    0.06
    .removeAttribute
    0.06
    ,'#
    0.06
    Act Density 0.007%

    No Known Activations