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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to legal and procedural contexts

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

    technical or code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    package
    -0.52
    ↵↵
    -0.50
    .
    -0.44
    InputBorder
    -0.42
    <eos>
    -0.41
    
    -0.41
    A
    -0.41
    More
    -0.40
    ↵
    -0.40
    The
    -0.40
    POSITIVE LOGITS
     ब्रेकडाउन
    0.82
    دانشنامهٔ
    0.75
    postsleuth
    0.70
    tonsoft
    0.65
     Exacts
    0.65
    Hentet
    0.60
    PreInfinity
    0.59
    inSlope
    0.59
    قایناق‌لار
    0.58
    fromnode
    0.57
    Act Density 0.086%

    No Known Activations