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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collider
    -0.06
    mounted
    -0.06
    win
    -0.06
    ภ
    -0.06
     capitalists
    -0.06
    (M
    -0.06
    ring
    -0.06
    гля
    -0.06
    tras
    -0.06
    vet
    -0.06
    POSITIVE LOGITS
     TableCell
    0.08
    Protocol
    0.07
    .".
    0.06
     sel
    0.06
     عبدالله
    0.06
     Students
    0.06
    พวกเข
    0.06
     pož
    0.06
    Ze
    0.06
    ’une
    0.06
    Act Density 0.000%

    No Known Activations