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

    Neuronpedia

    INDEX
    Explanations

    professions and associated people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    0.35
    text
    0.35
    removed
    0.35
    did
    0.34
    redir
    0.34
    ｉ
    0.33
     ably
    0.33
    เป็น
    0.32
    idf
    0.31
    देश
    0.31
    POSITIVE LOGITS
     extraordinaire
    0.56
     وم
    0.49
     الك
    0.39
     וח
    0.38
     અને
    0.38
     ك
    0.37
     K
    0.37
     skupiny
    0.35
    കളിൽ
    0.35
     மற்றும்
    0.35
    Act Density 0.009%

    No Known Activations