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

    Neuronpedia

    INDEX
    Explanations

    contrast or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .`);
    0.42
     আজকে
    0.41
    ،
    0.41
     Потому
    0.38
    "،
    0.38
    お店
    0.37
    攵
    0.37
    交往
    0.37
     এছাড়াও
    0.37
     Aside
    0.36
    POSITIVE LOGITS
     defying
    0.58
     lest
    0.57
     though
    0.55
    though
    0.55
     scarcely
    0.55
     devoid
    0.54
     necessitating
    0.50
    leaving
    0.49
     unmistak
    0.49
    yet
    0.48
    Act Density 0.103%

    No Known Activations