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

    Neuronpedia

    INDEX
    Explanations

    confirmation dialog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logs
    0.76
    logs
    0.73
    Logs
    0.70
     Logs
    0.67
    💪
    0.65
     beforePath
    0.65
    estream
    0.64
    log
    0.64
     Rast
    0.62
     blog
    0.62
    POSITIVE LOGITS
     dialog
    1.76
    Dialog
    1.71
    dialog
    1.62
     dialogue
    1.57
     Dialog
    1.56
     diálogo
    1.55
    Confirmation
    1.51
     confirmation
    1.49
     popup
    1.48
     Confirmation
    1.47
    Act Density 0.234%

    No Known Activations