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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :event
    -0.07
    League
    -0.07
    ,left
    -0.07
     warrant
    -0.07
     άλλ
    -0.06
    经过
    -0.06
    ाच
    -0.06
     thử
    -0.06
    ณ
    -0.06
     jenom
    -0.06
    POSITIVE LOGITS
    рут
    0.07
     payday
    0.06
    波
    0.06
    े,
    0.06
     Washer
    0.06
    ़न
    0.06
    ,proto
    0.06
    966
    0.06
    cern
    0.06
    prix
    0.06
    Act Density 0.017%

    No Known Activations