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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     portraits
    -0.07
    Hy
    -0.07
     قص
    -0.06
     enamel
    -0.06
     Prophet
    -0.06
     Aerospace
    -0.06
    {↵↵
    -0.06
    thy
    -0.06
     الدولة
    -0.06
    -food
    -0.06
    POSITIVE LOGITS
    encoded
    0.06
    _sound
    0.06
    ;-
    0.06
    ิก
    0.06
    indices
    0.06
    (prev
    0.06
     fades
    0.06
     resolves
    0.06
     uns
    0.06
     shielding
    0.05
    Act Density 0.004%

    No Known Activations