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

    Neuronpedia

    INDEX
    Explanations

    qualifiers expressing small degrees or slight variations

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

    small degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @
    -0.35
     ados
    -0.33
     tall
    -0.32
    NET
    -0.32
     Hirsch
    -0.31
     Wiesen
    -0.31
    surname
    -0.31
     luas
    -0.31
     @
    -0.31
     Burk
    -0.30
    POSITIVE LOGITS
     sedikit
    1.06
    slightly
    0.99
     slightly
    0.95
    Slightly
    0.93
     leggermente
    0.91
     Slightly
    0.91
     slight
    0.90
     légèrement
    0.89
     bisschen
    0.86
     vähän
    0.86
    Act Density 0.037%

    No Known Activations