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

    Neuronpedia

    INDEX
    Explanations

    about "completely"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tox
    0.91
     soluble
    0.90
     influencer
    0.89
     smaller
    0.88
     prohibit
    0.88
     lethal
    0.88
    取决于
    0.88
     Bach
    0.87
     ornamental
    0.86
     sofa
    0.86
    POSITIVE LOGITS
    𝙪
    0.89
    ಙ
    0.89
    דה
    0.88
    आ
    0.87
    廾
    0.87
     Après
    0.85
     oWord
    0.84
    ку
    0.84
    പു
    0.84
    𝙥
    0.83
    Act Density 0.000%

    No Known Activations