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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руется
    -0.07
    Regex
    -0.07
     coun
    -0.06
    omen
    -0.06
     getState
    -0.06
    nych
    -0.06
     های
    -0.06
    pr
    -0.06
    west
    -0.06
     Potato
    -0.06
    POSITIVE LOGITS
    (atom
    0.07
    技能
    0.06
     disqualified
    0.06
     CDN
    0.06
     stalk
    0.06
    ��글
    0.06
    resentation
    0.06
     아니
    0.06
    ТО
    0.06
    ↵↵
    0.06
    Act Density 0.057%

    No Known Activations