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

    Neuronpedia

    INDEX
    Explanations

    patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Grid
    -0.07
     Bard
    -0.07
     Pes
    -0.06
    _timezone
    -0.06
     Besides
    -0.06
     absl
    -0.06
     AppState
    -0.06
    .Views
    -0.06
     ท
    -0.06
     ovšem
    -0.06
    POSITIVE LOGITS
    ční
    0.07
    емого
    0.07
    ному
    0.07
    (Output
    0.07
     transport
    0.07
    orum
    0.07
     lingu
    0.06
    ري
    0.06
     tracer
    0.06
     lineNumber
    0.06
    Act Density 0.013%

    No Known Activations