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

    Neuronpedia

    INDEX
    Explanations

    antibody

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ścian
    -0.10
     Pump
    -0.07
     рем
    -0.07
    돋
    -0.07
    电解
    -0.07
    𝘞
    -0.07
    入场
    -0.07
     الجنس
    -0.07
     inspections
    -0.06
    Unused
    -0.06
    POSITIVE LOGITS
    sci
    0.07
     Ac
    0.07
    pur
    0.07
    audi
    0.07
    {-
    0.07
     PSG
    0.07
    opoulos
    0.06
     many
    0.06
     HO
    0.06
    elist
    0.06
    Act Density 0.010%

    No Known Activations