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

    Neuronpedia

    INDEX
    Explanations

    audio/image file format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .When
    -0.07
    	Label
    -0.07
    .pay
    -0.06
     scanf
    -0.06
     Wants
    -0.06
     defer
    -0.06
    _HALF
    -0.06
    herits
    -0.06
    xlabel
    -0.06
    parent
    -0.06
    POSITIVE LOGITS
     ainsi
    0.07
    يك
    0.07
     ekip
    0.06
    ΣΤ
    0.06
     confirmation
    0.06
     unknow
    0.06
     prime
    0.06
     ром
    0.06
     Secret
    0.06
    -haired
    0.06
    Act Density 0.016%

    No Known Activations