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

    Neuronpedia

    INDEX
    Explanations

    acknowledging imperfection and inevitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द्वारे
    0.37
    user
    0.36
    encoding
    0.36
     firebase
    0.33
     toj
    0.33
    apache
    0.33
    {\$
    0.33
    ören
    0.32
     apache
    0.32
    簍
    0.32
    POSITIVE LOGITS
     sometimes
    0.71
     inevitable
    0.69
     inev
    0.65
     parfois
    0.64
     imperfect
    0.64
     inevitably
    0.64
     Sometimes
    0.63
    Sometimes
    0.63
     unavoid
    0.63
     иногда
    0.62
    Act Density 0.294%

    No Known Activations