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

    Neuronpedia

    INDEX
    Explanations

    legal contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Places
    -0.08
     Billion
    -0.07
     Doc
    -0.06
    asal
    -0.06
     alliances
    -0.06
     wholesale
    -0.06
     voluntary
    -0.06
    HB
    -0.06
     Quote
    -0.06
    -house
    -0.06
    POSITIVE LOGITS
     earthquake
    0.07
    LIB
    0.06
    ौकर
    0.06
    일에
    0.06
    TriState
    0.06
    -length
    0.06
    .randomUUID
    0.06
    ωμα
    0.06
    ají
    0.05
    드는
    0.05
    Act Density 0.020%

    No Known Activations