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

    Neuronpedia

    INDEX
    Explanations

    energy generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="#">
    -0.07
     jq
    -0.07
    divider
    -0.06
    gradable
    -0.06
    Shader
    -0.06
    PRS
    -0.06
     IGNORE
    -0.06
    μα
    -0.06
    Interesting
    -0.06
    Contracts
    -0.06
    POSITIVE LOGITS
     behaviors
    0.07
     behaviours
    0.07
    setting
    0.06
     emergence
    0.06
     büyük
    0.06
    _wait
    0.06
     involved
    0.06
     precision
    0.06
     nelle
    0.06
     عشق
    0.06
    Act Density 0.023%

    No Known Activations