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

    Neuronpedia

    INDEX
    Explanations

    word followed by punctuation or conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raining
    0.47
    -
    0.46
     Falcon
    0.44
     charging
    0.44
     baixa
    0.44
    。
    0.42
    0.42
    linux
    0.41
    nhof
    0.41
     изпъл
    0.41
    POSITIVE LOGITS
    കള്‍
    0.53
    พัน
    0.53
    兩種
    0.49
    Dam
    0.48
    快樂
    0.48
    ﾁ
    0.48
    കൾ
    0.48
    നങ്ങൾ
    0.47
    楽しい
    0.46
    खेल
    0.46
    Act Density 0.003%

    No Known Activations