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

    Neuronpedia

    INDEX
    Explanations

    instances of evaluation and numeric parameters in a technical context

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

    verbs or predicate adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ḗ
    -0.36
    机
    -0.36
    립
    -0.35
    maximum
    -0.33
    arsa
    -0.32
     Як
    -0.32
    경
    -0.31
     calorías
    -0.31
     backward
    -0.31
    omina
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.63
     createSlice
    0.60
     resourceCulture
    0.60
     pinulongan
    0.59
    DockStyle
    0.58
     noDo
    0.58
    endregion
    0.54
    endpush
    0.54
    AndEndTag
    0.51
    ">—
    0.50
    Act Density 0.001%

    No Known Activations