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

    Neuronpedia

    INDEX
    Explanations

    start your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     భూ
    0.86
    ங்கிணை
    0.76
     topological
    0.70
    야
    0.69
     ಭೂ
    0.68
     forested
    0.68
     Оте
    0.68
     ограниче
    0.67
     القانون
    0.66
    ныгы
    0.66
    POSITIVE LOGITS
    These
    0.72
     nonché
    0.70
    these
    0.68
     Estos
    0.66
    .'"
    0.66
     Essas
    0.66
    Estos
    0.66
     vinho
    0.65
    enos
    0.64
    मैं
    0.64
    Act Density 0.001%

    No Known Activations