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

    Neuronpedia

    INDEX
    Explanations

    qualifiers and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     가장
    0.63
     সবচেয়ে
    0.62
    만
    0.60
    豊富な
    0.59
    도
    0.59
     সবচে
    0.58
    자가
    0.58
    ರ್
    0.58
     montagnes
    0.58
    젠
    0.58
    POSITIVE LOGITS
    t
    0.83
    at
    0.77
    ↵
    0.75
    in
    0.68
    us
    0.68
    ↵↵
    0.67
    an
    0.67
    tions
    0.66
    l
    0.63
    ,"
    0.63
    Act Density 1.151%

    No Known Activations