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

    Neuronpedia

    INDEX
    Explanations

    `in a`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrog
    0.46
    줍니다
    0.45
    роди
    0.45
    чением
    0.44
    議論
    0.44
    كم
    0.44
    𝚣
    0.44
    гру
    0.44
    годно
    0.43
    栦
    0.43
    POSITIVE LOGITS
     PFAS
    0.49
     Y
    0.46
     Obituary
    0.46
    st
    0.44
    oppel
    0.44
     HEALTH
    0.41
    FICATION
    0.41
     vibrations
    0.41
     نکات
    0.41
     Groundwater
    0.41
    Act Density 0.001%

    No Known Activations