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

    Neuronpedia

    INDEX
    Explanations

    computer and math subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VALLEY
    0.44
    🪴
    0.41
    🛖
    0.40
     RESER
    0.39
     clamping
    0.38
    置
    0.38
    野
    0.38
    Valley
    0.37
     SAMPLE
    0.37
     yoktur
    0.36
    POSITIVE LOGITS
    ffes
    0.43
    Š
    0.43
     svak
    0.40
    etric
    0.40
    کھ
    0.39
    سی
    0.39
    computer
    0.39
     Sikk
    0.39
    astaan
    0.39
    agger
    0.39
    Act Density 0.000%

    No Known Activations