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

    Neuronpedia

    INDEX
    Explanations

    console commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    0.52
    き
    0.51
     sanguin
    0.48
    ح
    0.48
     skupiny
    0.47
    ukawa
    0.47
    ER
    0.47
    ://
    0.47
     kaug
    0.47
    मा
    0.47
    POSITIVE LOGITS
    ה
    0.59
    LOTREntity
    0.55
     რომლებიც
    0.53
     étude
    0.52
    Ｆ
    0.52
    esque
    0.52
    ized
    0.50
     accented
    0.50
    ේ
    0.50
    ის
    0.49
    Act Density 0.001%

    No Known Activations