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

    Neuronpedia

    INDEX
    Explanations

    doses and prevention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.71
    ,
    0.64
     table
    0.57
     widget
    0.56
     polarizing
    0.56
    ?
    0.55
     tables
    0.52
     in
    0.51
    !
    0.51
     shot
    0.50
    POSITIVE LOGITS
    obtenir
    0.78
    dimensioni
    0.78
    тивних
    0.77
     lumière
    0.76
     فیصلہ
    0.76
     Dès
    0.76
    કમ
    0.75
    Dims
    0.75
    └──
    0.75
    тивных
    0.75
    Act Density 2.347%

    No Known Activations