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

    Neuronpedia

    INDEX
    Explanations

    starting phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     budete
    0.77
     gjøre
    0.75
     Jangan
    0.74
    𝙉
    0.73
    ﯿ
    0.73
     Did
    0.72
    Pyrazole
    0.71
     будете
    0.71
     আপনার
    0.70
     Faça
    0.70
    POSITIVE LOGITS
     business
    0.77
     although
    0.75
    ;
    0.75
     though
    0.71
     desses
    0.70
    ¢
    0.68
    m
    0.67
    business
    0.67
     or
    0.66
    ier
    0.66
    Act Density 0.029%

    No Known Activations