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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TextFormField
    -0.61
    ganan
    -0.54
    astify
    -0.52
    нале
    -0.51
    ThroughAttribute
    -0.51
    parsedMessage
    -0.51
     cadre
    -0.50
    SourceChecksum
    -0.50
    cadre
    -0.48
     benchmarks
    -0.48
    POSITIVE LOGITS
    mybatisplus
    0.82
    tagHelperRunner
    0.71
    ⓧ
    0.71
    seamnă
    0.70
     hâte
    0.70
     stället
    0.68
     moindre
    0.68
     jouets
    0.63
    kijken
    0.63
     prédé
    0.63
    Act Density 0.001%

    No Known Activations