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

    Neuronpedia

    INDEX
    Explanations

    concentration of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.88
    .
    0.76
    :
    0.74
    ;
    0.72
    ,
    0.72
    。
    0.71
    ),
    0.69
    y
    0.69
    .)
    0.67
    f
    0.67
    POSITIVE LOGITS
     ሁሉም
    0.77
     większość
    0.70
     paraissent
    0.64
     abrang
    0.64
     certains
    0.63
     conoc
    0.63
    各类
    0.63
     các
    0.63
     sensibles
    0.63
     atténuées
    0.62
    Act Density 0.029%

    No Known Activations