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

    Neuronpedia

    INDEX
    Explanations

    introducing examples or specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obstante
    0.40
    Assume
    0.37
     Otras
    0.37
    Якщо
    0.37
    /_
    0.36
    What
    0.35
     verbo
    0.35
    Within
    0.34
    டன்
    0.34
    )+
    0.33
    POSITIVE LOGITS
     such
    1.89
     مثل
    1.81
    such
    1.78
     including
    1.74
     таких
    1.73
     poput
    1.72
     kuten
    1.69
     เช่น
    1.66
    including
    1.63
     like
    1.63
    Act Density 0.052%

    No Known Activations