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

    Neuronpedia

    INDEX
    Explanations

    24/7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lot
    0.38
     WAIT
    0.38
    ড়ো
    0.38
     impatience
    0.37
    ารณา
    0.37
    ство
    0.37
     bark
    0.36
    忍不住
    0.36
     Milton
    0.35
     FileResource
    0.35
    POSITIVE LOGITS
     prism
    0.38
    ',
    0.38
    angga
    0.37
     chaque
    0.36
    wię
    0.36
     года
    0.36
    ians
    0.35
    igue
    0.34
    varia
    0.34
     allev
    0.33
    Act Density 0.002%

    No Known Activations