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

    Neuronpedia

    INDEX
    Explanations

    no, sa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.80
    こともある
    1.50
    ির
    1.48
     tante
    1.44
    を描
    1.41
    を開催
    1.41
     nacionais
    1.40
    erving
    1.38
     choses
    1.33
    она
    1.30
    POSITIVE LOGITS
    ﻞ
    1.74
    ING
    1.59
    る
    1.58
    其他
    1.47
     undercut
    1.47
    ların
    1.45
    ssss
    1.45
     remit
    1.44
    ﻢ
    1.44
    ness
    1.43
    Act Density 0.174%

    No Known Activations