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

    Neuronpedia

    INDEX
    Explanations

    Company

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    史
    -0.07
     dug
    -0.07
     logged
    -0.07
    _fps
    -0.07
    农历
    -0.07
     thought
    -0.07
     Unauthorized
    -0.07
    �
    -0.07
     обо
    -0.07
     explored
    -0.06
    POSITIVE LOGITS
     Ripple
    0.07
     mejores
    0.07
    KeyUp
    0.06
    可怕
    0.06
    _Osc
    0.06
    越南
    0.06
    刺客
    0.06
     voksen
    0.06
     Speakers
    0.06
     כלומר
    0.06
    Act Density 0.012%

    No Known Activations