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

    Neuronpedia

    INDEX
    Explanations

    option 2, other options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वेदनशील
    0.71
    jähr
    0.70
    ürdig
    0.69
     nedir
    0.67
     zákon
    0.66
     CCc
    0.65
    arrerol
    0.65
     २०२२
    0.64
     způso
    0.63
    Чтобы
    0.63
    POSITIVE LOGITS
    ,
    0.80
    .
    0.65
    :
    0.64
     ،
    0.56
     attempted
    0.55
    ،
    0.55
    ;
    0.55
     encode
    0.54
    0.54
     pairs
    0.53
    Act Density 0.231%

    No Known Activations