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

    Neuronpedia

    INDEX
    Explanations

    depend on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lobin
    0.47
     추천
    0.43
    ")->
    0.43
     told
    0.42
     kitap
    0.42
     said
    0.41
     recommends
    0.41
     saath
    0.41
     pelvic
    0.41
     py
    0.41
    POSITIVE LOGITS
    ByUser
    0.48
    充滿
    0.48
    iera
    0.47
    agements
    0.46
    有助于
    0.44
    全新的
    0.44
    充满
    0.43
    ент
    0.43
    वाची
    0.42
     нового
    0.42
    Act Density 0.009%

    No Known Activations