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

    Neuronpedia

    INDEX
    Explanations

    including explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xứng
    0.35
     revolving
    0.30
     combining
    0.29
    كنولوجيا
    0.29
    寇
    0.29
     adding
    0.28
     fined
    0.28
     intersecting
    0.28
    iven
    0.28
    不同的
    0.28
    POSITIVE LOGITS
     explanations
    0.82
     descriptions
    0.77
     screenshots
    0.74
     explanation
    0.73
     описание
    0.68
     description
    0.67
     examples
    0.66
     instructions
    0.65
     diagrams
    0.63
     photographs
    0.63
    Act Density 0.044%

    No Known Activations