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

    Neuronpedia

    INDEX
    Explanations

    /api

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engraved
    -0.08
     vending
    -0.07
     estos
    -0.07
    .da
    -0.07
     خاطر
    -0.07
     lado
    -0.06
    กรณ
    -0.06
    _kv
    -0.06
     Fay
    -0.06
    κολ
    -0.06
    POSITIVE LOGITS
    TER
    0.06
    PLEMENT
    0.06
     SAF
    0.06
     Milton
    0.06
    وک
    0.06
     rooft
    0.06
    (tm
    0.05
     transforming
    0.05
     {}),↵
    0.05
     bol
    0.05
    Act Density 0.000%

    No Known Activations