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

    Neuronpedia

    INDEX
    Explanations

    training models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Va
    -0.07
    _call
    -0.07
     Moto
    -0.06
    mitters
    -0.06
    NotEmpty
    -0.06
     exchanging
    -0.06
    师
    -0.06
     Birliği
    -0.06
    ुव
    -0.06
    .ht
    -0.06
    POSITIVE LOGITS
     fatalError
    0.07
     fencing
    0.07
     ước
    0.07
     Automated
    0.06
     chiếc
    0.06
    hic
    0.06
    _usage
    0.06
    skills
    0.06
    =length
    0.06
     Olson
    0.06
    Act Density 0.017%

    No Known Activations