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

    Neuronpedia

    INDEX
    Explanations

    phrases and references to singular entities or instances, particularly in the context of processes or systems

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

    only one, single, once

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balleur
    -0.60
    expandindo
    -0.52
    Hochspringen
    -0.52
     Templar
    -0.50
     surla
    -0.49
     ब्रेकडाउन
    -0.48
    Viited
    -0.48
    Географиясе
    -0.47
     становника
    -0.47
     препратки
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.44
    One
    0.39
     Roskov
    0.39
    Only
    0.38
    RectangleBorder
    0.37
    Once
    0.37
     unless
    0.36
    Single
    0.36
    EXACT
    0.36
    unless
    0.35
    Act Density 0.054%

    No Known Activations