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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bip
    -0.07
    apiro
    -0.06
     Violet
    -0.06
    orz
    -0.06
     खतर
    -0.06
     znam
    -0.06
     لأن
    -0.06
     Equal
    -0.06
     Voter
    -0.06
     truck
    -0.06
    POSITIVE LOGITS
    ····
    0.07
    licht
    0.06
     đảo
    0.06
     misdemean
    0.06
    SERVER
    0.06
    ội
    0.06
     odkazy
    0.06
     spacer
    0.06
    tparam
    0.06
    PERSON
    0.06
    Act Density 0.340%

    No Known Activations