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

    Neuronpedia

    INDEX
    Explanations

    `entity` definitions and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ⚫
    0.55
    pO
    0.49
    gaussian
    0.48
    nY
    0.46
     exposureButton
    0.44
     williams
    0.43
    vartheta
    0.42
    mockito
    0.42
    ických
    0.42
    zeichnung
    0.41
    POSITIVE LOGITS
     Fifty
    0.42
     Beside
    0.41
    仅
    0.41
     Bypass
    0.40
     Promise
    0.39
     Noon
    0.39
     Website
    0.38
     Work
    0.38
     Abroad
    0.38
     Forty
    0.38
    Act Density 1.095%

    No Known Activations