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

    Neuronpedia

    INDEX
    Explanations

    words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    怀孕
    0.48
     líderes
    0.47
     délais
    0.47
    ሁሉም
    0.45
     فريبي
    0.45
     imperio
    0.45
    jobSize
    0.44
     মিনি
    0.44
     grapple
    0.44
     screech
    0.44
    POSITIVE LOGITS
    s
    0.59
     an
    0.52
    sl
    0.48
    y
    0.48
    in
    0.47
    ,
    0.46
    اج
    0.46
    t
    0.46
    set
    0.46
    g
    0.45
    Act Density 0.000%

    No Known Activations