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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    can
    -0.07
     Mi
    -0.07
     analyzes
    -0.07
    ա�
    -0.06
     cows
    -0.06
    racak
    -0.06
    _cmds
    -0.06
     princess
    -0.06
    ickers
    -0.06
    capability
    -0.06
    POSITIVE LOGITS
     عنوان
    0.07
    istica
    0.07
     تصو
    0.06
     身
    0.06
    .Of
    0.06
     appropriate
    0.06
    ease
    0.06
    _export
    0.06
     Unique
    0.06
    ั้
    0.06
    Act Density 0.062%

    No Known Activations