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

    Neuronpedia

    INDEX
    Explanations

    giving examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TLS
    -0.07
     wood
    -0.06
    cdf
    -0.06
    .xrTableCell
    -0.06
     parasite
    -0.06
    خان
    -0.06
    _walk
    -0.06
     بالاتر
    -0.06
    beans
    -0.06
     zs
    -0.06
    POSITIVE LOGITS
     Sof
    0.06
     atoi
    0.06
     tragedy
    0.06
     आग
    0.06
    vekili
    0.06
    _game
    0.06
    ichen
    0.06
    _MEMORY
    0.06
     '\''
    0.06
     concluding
    0.06
    Act Density 0.331%

    No Known Activations