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

    Neuronpedia

    INDEX
    Explanations

    button clicks or presses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    手上
    0.37
     stimulated
    0.34
    परि
    0.33
     Sc
    0.33
    leveland
    0.33
     porad
    0.32
    ৌর
    0.32
     Childhood
    0.32
    णारी
    0.32
    flashdata
    0.32
    POSITIVE LOGITS
     submit
    0.86
    Submit
    0.85
     Submit
    0.85
     кнопку
    0.84
    startButton
    0.84
    UpdateButton
    0.84
     botón
    0.83
     botao
    0.82
     button
    0.80
    按钮
    0.77
    Act Density 0.030%

    No Known Activations