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

    Neuronpedia

    INDEX
    Explanations

    list length checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    尚未
    0.38
    渥
    0.35
    CUIT
    0.35
     изначально
    0.34
     кандида
    0.34
     उम्मीदवार
    0.34
     थी
    0.34
     Candidates
    0.33
     후보
    0.33
    INTS
    0.33
    POSITIVE LOGITS
     using
    0.42
     playing
    0.40
     reading
    0.37
     palliative
    0.37
     graphical
    0.36
     played
    0.36
     panels
    0.36
    degenerative
    0.35
    okh
    0.35
     centres
    0.34
    Act Density 0.003%

    No Known Activations