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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heimer
    -0.07
    textBox
    -0.06
     engages
    -0.06
     Ames
    -0.06
    .TextField
    -0.06
     detr
    -0.06
    _text
    -0.06
     Americ
    -0.06
     Ending
    -0.06
    cwd
    -0.06
    POSITIVE LOGITS
    sizlik
    0.06
     _|
    0.06
    ูปแบบ
    0.06
    ,’”
    0.06
    络
    0.06
     天
    0.06
    785
    0.06
    handleChange
    0.06
     Highly
    0.05
    confirmation
    0.05
    Act Density 0.033%

    No Known Activations