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

    Neuronpedia

    INDEX
    Explanations

    references to confinement or restraint, particularly in relation to shackles and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sha words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.46
     ύ
    -0.45
    onOptions
    -0.44
     fico
    -0.42
    Παραπομπές
    -0.41
     CreateTagHelper
    -0.41
     MessageBoxIcon
    -0.40
    PDOException
    -0.39
     Uint
    -0.38
    PointerException
    -0.38
    POSITIVE LOGITS
     sha
    1.67
    sha
    0.86
     Shape
    0.85
     Shak
    0.84
     shack
    0.83
     shape
    0.82
    SHAPE
    0.82
     SHAPE
    0.80
     Shack
    0.80
    shape
    0.79
    Act Density 0.005%

    No Known Activations