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

    Neuronpedia

    INDEX
    Explanations

    tell me for specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    about
    0.60
     about
    0.59
     ABOUT
    0.54
     acerca
    0.54
    ABOUT
    0.52
    ']+
    0.50
     về
    0.50
     hakkında
    0.49
    About
    0.49
    เกี่ยวกับ
    0.49
    POSITIVE LOGITS
    反応
    0.44
     Interests
    0.39
     reactions
    0.38
    PopupWindowStyle
    0.38
    cosity
    0.37
    жин
    0.37
     interests
    0.37
    toned
    0.36
     তুমি
    0.36
    genre
    0.36
    Act Density 0.010%

    No Known Activations