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

    Neuronpedia

    INDEX
    Explanations

    numeric values and identifiers, likely indicating legal or patent references

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

    Japanese patent references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.66
     étoient
    -0.60
    lámpara
    -0.54
     miniaturka
    -0.52
     Grüsse
    -0.52
     Italij
    -0.52
     pouvoit
    -0.51
     milioane
    -0.51
     uș
    -0.50
     Humanos
    -0.50
    POSITIVE LOGITS
    verifyException
    0.49
     Zu
    0.48
    CppMethod
    0.48
    Zu
    0.46
    #
    0.45
     ZF
    0.45
     Boyd
    0.45
    ActionMode
    0.43
    dsl
    0.42
    ModelAdmin
    0.42
    Act Density 0.056%

    No Known Activations