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

    Neuronpedia

    INDEX
    Explanations

    call me or call out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einf
    0.45
     êtes
    0.45
    ي
    0.44
    ত্ব
    0.44
     nhưng
    0.44
     ót
    0.44
     dư
    0.43
     serán
    0.43
    ние
    0.43
     taxed
    0.42
    POSITIVE LOGITS
    h
    0.58
    l
    0.57
    n
    0.55
    v
    0.55
    sp
    0.54
    module
    0.45
    action
    0.44
    m
    0.44
    map
    0.44
    api
    0.44
    Act Density 0.069%

    No Known Activations