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

    Neuronpedia

    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Seconds
    -0.07
     LEN
    -0.07
    _neighbors
    -0.07
    ANNER
    -0.07
    _image
    -0.07
    /Branch
    -0.07
    :")
    -0.07
    Ger
    -0.07
     सर
    -0.06
     perpetrator
    -0.06
    POSITIVE LOGITS
     composition
    0.09
     compositions
    0.07
     fauna
    0.07
    105
    0.07
    holding
    0.07
     content
    0.06
    columns
    0.06
     stehen
    0.06
     Elegant
    0.06
    šla
    0.06
    Act Density 0.016%

    No Known Activations