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

    Neuronpedia

    INDEX
    Explanations

    /science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abo
    0.73
     постав
    0.72
    もので
    0.70
     aspirations
    0.69
     Vorsch
    0.67
     mse
    0.66
    ものです
    0.65
     um
    0.64
     prior
    0.64
     rhe
    0.63
    POSITIVE LOGITS
    exists
    0.72
    সংখ্যক
    0.71
    erat
    0.71
    复杂的
    0.71
    acat
    0.71
     tenté
    0.71
    azen
    0.68
    Attachment
    0.68
    security
    0.68
    वलं
    0.68
    Act Density 0.004%

    No Known Activations