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

    Neuronpedia

    INDEX
    Explanations

    elements associated with mathematical structures and expressions

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

    `Att_R`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SDLK
    -0.45
    ervlak
    -0.41
     vengo
    -0.40
    pholes
    -0.39
    MessageOf
    -0.38
     fieldNum
    -0.37
     PyLong
    -0.35
     turns
    -0.35
     padx
    -0.35
     uy
    -0.34
    POSITIVE LOGITS
     purpoſe
    0.52
     disambiguazione
    0.49
     Infórmanos
    0.48
     pleaſure
    0.43
    ьаж
    0.43
    évaluateur
    0.43
     Anſ
    0.42
    BASELINE
    0.42
    __(/*!
    0.42
    ệc
    0.41
    Act Density 0.274%

    No Known Activations