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

    Neuronpedia

    INDEX
    Explanations

    rise or exploit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    varlak
    0.70
    钣
    0.66
     compactness
    0.66
    డింది
    0.66
    ullie
    0.66
     Fleisch
    0.65
    徳
    0.64
    uninstall
    0.63
     компакт
    0.62
     deaktiv
    0.62
    POSITIVE LOGITS
     rise
    3.61
     rises
    3.41
     rising
    3.36
     Rise
    3.09
    rise
    2.96
     risen
    2.89
     Rising
    2.85
     climb
    2.85
    Rise
    2.84
    rising
    2.83
    Act Density 0.525%

    No Known Activations