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

    Neuronpedia

    INDEX
    Explanations

    database names, drugs, locations, software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chuột
    0.49
    가는
    0.48
    GON
    0.48
     자기
    0.47
     duckys
    0.47
     abhiv
    0.46
    ㄑ
    0.45
     drawed
    0.44
     tzv
    0.43
     vitth
    0.43
    POSITIVE LOGITS
    ن
    0.60
     and
    0.56
    ↵
    0.55
    2
    0.55
    н
    0.55
    на
    0.54
    ق
    0.53
    aren
    0.51
    water
    0.51
    ’
    0.51
    Act Density 0.251%

    No Known Activations