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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ritos
    -0.07
    "In
    -0.07
    bounded
    -0.07
    以上
    -0.06
    学院
    -0.06
     않는
    -0.06
    Telegram
    -0.06
    Georgia
    -0.06
     Xen
    -0.06
    ி
    -0.06
    POSITIVE LOGITS
     funkc
    0.07
    (fout
    0.07
    Skill
    0.06
    /card
    0.06
    _break
    0.06
    .ErrorMessage
    0.06
    _resp
    0.06
    พระราช
    0.06
    рукт
    0.06
     TERM
    0.06
    Act Density 0.488%

    No Known Activations