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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pictures
    -0.07
    财
    -0.06
    enin
    -0.06
     vice
    -0.06
     Income
    -0.06
    292
    -0.06
    frog
    -0.06
     quotations
    -0.06
    era
    -0.06
    ared
    -0.06
    POSITIVE LOGITS
     posY
    0.07
    _GAIN
    0.07
     actualizar
    0.06
     granite
    0.06
    vatel
    0.06
     �
    0.06
    ुरक
    0.06
     Skyl
    0.06
    (""),
    0.06
    *angstrom
    0.06
    Act Density 0.030%

    No Known Activations