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

    Neuronpedia

    INDEX
    Explanations

    brake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lists
    -0.07
    Seek
    -0.07
     Panasonic
    -0.07
    (optimizer
    -0.06
    annual
    -0.06
    KeyValuePair
    -0.06
    _grad
    -0.06
     Below
    -0.06
    .peek
    -0.06
     гла
    -0.06
    POSITIVE LOGITS
    />↵
    0.08
     перем
    0.06
     Green
    0.06
    staff
    0.06
    ters
    0.06
     stroke
    0.06
     sling
    0.06
     pret
    0.06
     SCI
    0.06
     Principal
    0.06
    Act Density 0.007%

    No Known Activations