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

    Neuronpedia

    INDEX
    Explanations

    month

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    masters
    -0.07
    (resources
    -0.07
     ammon
    -0.07
     Holding
    -0.06
     throw
    -0.06
     messaging
    -0.06
     ngu
    -0.06
     黄
    -0.06
     Shapes
    -0.06
     connectors
    -0.06
    POSITIVE LOGITS
     어머니
    0.07
    hap
    0.06
    emy
    0.06
    accel
    0.06
    getCode
    0.06
     �
    0.06
     оформ
    0.06
     ､
    0.06
     Gem
    0.06
     demean
    0.06
    Act Density 0.024%

    No Known Activations