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

    Neuronpedia

    INDEX
    Explanations

    it's nice to meet you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;#
    0.43
    джу
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.41
    کم
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.39
     -"
    0.39
    נן
    0.39
    nms
    0.39
    *$
    0.38
    POSITIVE LOGITS
     …
    0.48
    ……
    0.44
     मगर
    0.40
     ….
    0.39
     فيما
    0.39
     CH
    0.39
    …</
    0.39
    …
    0.38
     …,
    0.37
    ….
    0.37
    Act Density 0.003%

    No Known Activations