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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     willen
    -0.07
    CHANGE
    -0.07
    'un
    -0.07
     %.
    -0.06
    ccording
    -0.06
     정도
    -0.06
     PHP
    -0.06
    -wing
    -0.06
     ○
    -0.06
     summary
    -0.06
    POSITIVE LOGITS
     fearful
    0.07
    zym
    0.06
    ropical
    0.06
     arresting
    0.06
     капит
    0.06
    ateral
    0.06
     scrolled
    0.06
    .chart
    0.05
    ับม
    0.05
     Yar
    0.05
    Act Density 0.020%

    No Known Activations