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

    Neuronpedia

    INDEX
    Explanations

    doing tasks and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creciente
    0.43
    Ꮭ
    0.43
     князя
    0.42
     linkCell
    0.42
    깨
    0.41
     средне
    0.41
     резко
    0.41
    𒊩
    0.41
     분명
    0.41
    쟈
    0.41
    POSITIVE LOGITS
     research
    0.49
    le
    0.46
     researches
    0.45
     Research
    0.44
     solve
    0.44
     multitasking
    0.43
    research
    0.42
    navigations
    0.41
     Recherches
    0.41
     experiments
    0.40
    Act Density 0.007%

    No Known Activations