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

    Neuronpedia

    INDEX
    Explanations

    attempting to match

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vielzahl
    0.30
    waters
    0.28
    Day
    0.28
    các
    0.27
    4
    0.27
     dnia
    0.27
    多
    0.27
    日
    0.26
     മേഖല
    0.26
    weekend
    0.26
    POSITIVE LOGITS
     попыта
    0.30
     attempting
    0.27
     attempt
    0.26
     attempted
    0.26
     recipe
    0.25
    하려고
    0.25
     advertising
    0.25
     attempts
    0.24
     borrowed
    0.24
    attempt
    0.24
    Act Density 0.310%

    No Known Activations