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

    Neuronpedia

    INDEX
    Explanations

    two hearts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mock
    0.52
    0.48
    Mock
    0.46
    Text
    0.45
    mock
    0.45
     vst
    0.45
     scan
    0.45
    am
    0.43
     questionnaire
    0.43
    udiante
    0.42
    POSITIVE LOGITS
     کاهش
    0.47
    誦
    0.46
     maksimum
    0.45
    ീക
    0.45
     Ä
    0.44
     смотря
    0.44
    อย่าง
    0.43
     आठ
    0.43
    lebihan
    0.43
     Kombat
    0.43
    Act Density 0.010%

    No Known Activations