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

    Neuronpedia

    INDEX
    Explanations

    Ore/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gonic
    -0.67
     MainAxisSize
    -0.66
     ModelExpression
    -0.54
    googleapis
    -0.54
    hoga
    -0.51
    teen
    -0.50
    солю
    -0.50
     Biôgrafia
    -0.50
    ome
    -0.48
    OM
    -0.48
    POSITIVE LOGITS
     Carboniferous
    0.59
     '\\;'
    0.56
    Eigenschaften
    0.55
    <bos>
    0.51
    ValueGenerated
    0.51
    LookAnd
    0.50
     Cuth
    0.49
    perties
    0.49
     torto
    0.49
    gridx
    0.48
    Act Density 0.059%

    No Known Activations