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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and their results

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

    solve for variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thus
    -0.33
     [
    -0.31
     découvertes
    -0.30
    //
    -0.30
    GenerationType
    -0.29
    BarButtonItem
    -0.28
    HORIZONTAL
    -0.28
     Dr
    -0.27
     Project
    -0.27
     fæ
    -0.27
    POSITIVE LOGITS
     zwiſchen
    0.75
     ſind
    0.75
    ſſung
    0.74
    ஦
    0.73
     ब्रेकडाउन
    0.73
    <unused8>
    0.73
    <unused41>
    0.72
    <unused74>
    0.72
    <unused28>
    0.72
    <unused14>
    0.72
    Act Density 0.518%

    No Known Activations