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

    Neuronpedia

    INDEX
    Explanations

    words indicating something bad is happening to something or someone.

    oai_token-act-pair · gemini-2.0-flash

    Opinions and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.85
     utafitiHapana
    -0.81
    AndEndTag
    -0.78
    ьаж
    -0.69
    存于互联网档案馆
    -0.69
     تانيه
    -0.68
    rungsseite
    -0.66
    Tembelea
    -0.66
    -0.65
    原始内容存档于
    -0.64
    POSITIVE LOGITS
     who
    0.75
     whom
    0.69
     him
    0.67
    Whom
    0.63
     hvem
    0.63
    Quien
    0.60
     Who
    0.59
    whom
    0.57
    who
    0.57
    Who
    0.56
    Act Density 7.542%

    No Known Activations