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

    Neuronpedia

    INDEX
    Explanations

    mode settings and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.67
    in
    1.52
    at
    1.51
     be
    1.50
    w
    1.40
     a
    1.39
    t
    1.39
     are
    1.37
    v
    1.33
    י
    1.33
    POSITIVE LOGITS
    モード
    1.22
     ánimo
    1.16
     режим
    1.09
    出産
    0.96
    것
    0.96
     ήταν
    0.95
     liberd
    0.95
     기타
    0.95
     Վ
    0.95
    ionante
    0.94
    Act Density 0.019%

    No Known Activations