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

    Neuronpedia

    INDEX
    Explanations

    words indicating potential success or effectiveness in research or therapies

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

    promising new approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sstil
    -0.43
     vacations
    -0.42
     totales
    -0.41
     obé
    -0.41
     leher
    -0.40
    cetines
    -0.40
    ajuku
    -0.40
     devoirs
    -0.40
     armor
    -0.40
     vectorielle
    -0.40
    POSITIVE LOGITS
     promising
    2.00
     promet
    1.13
     prome
    1.03
     promis
    1.02
    prom
    0.89
     Prom
    0.88
     prospects
    0.83
     promise
    0.83
     hopeful
    0.82
    Prom
    0.78
    Act Density 0.006%

    No Known Activations