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

    Neuronpedia

    INDEX
    Explanations

    seen it all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ःख
    1.43
    ب
    1.36
    ש
    1.29
    ן
    1.20
    かしい
    1.20
     means
    1.15
    Spare
    1.15
    yne
    1.14
    ालय
    1.13
    లో
    1.13
    POSITIVE LOGITS
     xét
    1.80
    вропей
    1.41
     footage
    1.41
     reagents
    1.39
     baseHP
    1.39
    ples
    1.37
    дру
    1.36
    娥
    1.35
    !\!\
    1.33
     afectada
    1.31
    Act Density 0.040%

    No Known Activations