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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ingram
    -0.07
     Platforms
    -0.07
     Relationship
    -0.06
     سطح
    -0.06
     Relationships
    -0.06
     facet
    -0.06
    pas
    -0.06
    )V
    -0.06
     Quar
    -0.06
    震
    -0.06
    POSITIVE LOGITS
    orex
    0.07
    render
    0.06
    /use
    0.06
    toFloat
    0.06
    _run
    0.06
     ordeal
    0.06
    /tiny
    0.06
    REGISTER
    0.06
     ActionType
    0.06
    _CID
    0.06
    Act Density 0.014%

    No Known Activations