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

    Neuronpedia

    INDEX
    Explanations

    Datatypes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feature
    -0.08
    _METADATA
    -0.07
    բ
    -0.07
    unist
    -0.07
     lj
    -0.07
     answered
    -0.07
    帮助
    -0.06
     ris
    -0.06
    截
    -0.06
     survived
    -0.06
    POSITIVE LOGITS
     ?>:</
    0.08
     barber
    0.07
     workstation
    0.07
    .What
    0.07
    outedEventArgs
    0.07
     dames
    0.07
     böl
    0.07
    expects
    0.07
     manuals
    0.07
     Dagger
    0.07
    Act Density 0.027%

    No Known Activations