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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSP
    -0.07
     -------------------------------------------------------------------------
    -0.07
     losing
    -0.07
    _MAJOR
    -0.06
    (-(
    -0.06
    elleicht
    -0.06
     spectrum
    -0.06
     Order
    -0.06
     XOR
    -0.06
     dati
    -0.06
    POSITIVE LOGITS
    �
    0.06
     SM
    0.06
    ्ञ
    0.06
    ě
    0.06
     brave
    0.06
    ữ
    0.06
    거
    0.06
    Ž
    0.06
    ả
    0.06
     Wilmington
    0.06
    Act Density 0.002%

    No Known Activations