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

    Neuronpedia

    INDEX
    Explanations

    open source software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cost
    -0.07
     Stap
    -0.07
     societal
    -0.07
     sealing
    -0.06
    anguage
    -0.06
    IZER
    -0.06
     potentials
    -0.06
     etc
    -0.06
    .CommandType
    -0.06
     Der
    -0.06
    POSITIVE LOGITS
    .Blocks
    0.06
    ssc
    0.06
    primaryKey
    0.06
    \Builder
    0.06
    izmet
    0.06
    InputElement
    0.06
     IOException
    0.06
    (signature
    0.06
     alış
    0.06
     důvod
    0.06
    Act Density 0.023%

    No Known Activations