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

    Neuronpedia

    INDEX
    Explanations

    references to academic or publishing entities, specifically presses

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

    University Press

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.52
    HasBeenSet
    -0.44
     humanistic
    -0.44
     igualdad
    -0.43
    Rüyada
    -0.42
     combattre
    -0.42
    Graduation
    -0.42
     olímp
    -0.41
     olympique
    -0.41
     Elimination
    -0.41
    POSITIVE LOGITS
     Press
    1.38
     PRESS
    0.93
    Press
    0.88
     press
    0.79
     Presses
    0.66
    verlag
    0.63
    出版社
    0.62
    談社
    0.57
     Publishers
    0.54
     Presse
    0.53
    Act Density 0.009%

    No Known Activations