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

    Neuronpedia

    INDEX
    Explanations

    underscores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /')
    -0.07
    _machine
    -0.07
    ा↵↵
    -0.06
     homic
    -0.06
    _position
    -0.06
     receiver
    -0.06
     Baseball
    -0.06
    .putExtra
    -0.06
    WATCH
    -0.06
    DataBase
    -0.06
    POSITIVE LOGITS
    roke
    0.06
     Ар
    0.06
    leh
    0.06
     QS
    0.06
    mr
    0.06
     plagiar
    0.06
     plur
    0.06
     згод
    0.06
     roadmap
    0.06
     evitar
    0.06
    Act Density 0.005%

    No Known Activations