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

    Neuronpedia

    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爾
    -0.07
     Scan
    -0.07
     UR
    -0.07
    укт
    -0.07
    信
    -0.07
     Phase
    -0.06
     tranny
    -0.06
     causal
    -0.06
     judged
    -0.06
     millennials
    -0.06
    POSITIVE LOGITS
     وت
    0.08
     ।
    0.06
    Credit
    0.06
     subsidy
    0.06
     vent
    0.06
     ierr
    0.06
    XR
    0.06
     فيلم
    0.06
    (pin
    0.06
    ه
    0.06
    Act Density 0.000%

    No Known Activations