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

    Neuronpedia

    INDEX
    Explanations

    references to high-level scientific concepts or terms

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

    archaic spellings and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.50
    abinieri
    -0.37
    ăți
    -0.35
     Maas
    -0.35
    بوابة
    -0.35
    fonos
    -0.35
     textual
    -0.34
     Mathis
    -0.34
     Delft
    -0.34
    URIDAD
    -0.34
    POSITIVE LOGITS
     ainfi
    0.64
     enfans
    0.61
     houſe
    0.60
    KURZBESCHREIBUNG
    0.60
    writeFieldEnd
    0.56
     ſte
    0.56
    twimg
    0.55
     betweenstory
    0.54
    SequentialGroup
    0.54
     picioare
    0.52
    Act Density 0.000%

    No Known Activations