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

    Neuronpedia

    INDEX
    Explanations

    software license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compute
    0.44
    olics
    0.43
    ídos
    0.43
    ދ
    0.41
     Flows
    0.39
     Damages
    0.38
    correcto
    0.38
    eroy
    0.37
     cherry
    0.36
    とし
    0.36
    POSITIVE LOGITS
    楲
    0.39
    πους
    0.39
    ---’
    0.38
    --“
    0.38
    --’
    0.38
    (--
    0.37
    鄴
    0.37
    คาร
    0.36
    在高
    0.35
     ју
    0.35
    Act Density 0.000%

    No Known Activations