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

    Neuronpedia

    INDEX
    Explanations

    effort and difficulty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parfois
    0.47
    റുണ്ട്
    0.45
    有时候
    0.44
     soms
    0.44
    明明
    0.44
     иногда
    0.43
    不够
    0.43
     třeba
    0.43
    Sometimes
    0.42
    好像
    0.42
    POSITIVE LOGITS
     attempting
    1.24
     attempts
    1.21
     Attempts
    1.15
     попы
    1.06
     realistically
    1.06
    Attempts
    1.06
     Attempt
    1.02
    attempts
    1.02
     attempt
    1.01
    Attempt
    0.96
    Act Density 0.068%

    No Known Activations