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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and elements that indicate structure or configuration

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

    extra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.58
    ########.
    -0.56
    enderror
    -0.49
    NameInMap
    -0.47
    errHandler
    -0.46
    GOTREF
    -0.45
     CreateTagHelper
    -0.45
    zelfde
    -0.44
     <>",
    -0.44
     voeten
    -0.43
    POSITIVE LOGITS
     extra
    1.52
    Extra
    1.41
     Extra
    1.40
    extra
    1.36
     EXTRA
    1.30
    EXTRA
    1.23
     ekstra
    1.21
     Extras
    0.94
     extras
    0.92
    extras
    0.89
    Act Density 0.020%

    No Known Activations