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

    Neuronpedia

    INDEX
    Explanations

    words after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symptoms
    0.73
     reported
    0.70
     jumped
    0.66
    ியும்
    0.65
     reporte
    0.65
     síntomas
    0.64
    jump
    0.64
     sintomi
    0.63
     compare
    0.62
     sintomas
    0.62
    POSITIVE LOGITS
     Options
    1.14
     Ideally
    0.94
     Preferably
    0.93
     Option
    0.92
     preferably
    0.91
     options
    0.91
     Customizable
    0.89
    options
    0.89
     customizable
    0.87
    Options
    0.86
    Act Density 0.358%

    No Known Activations