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

    Neuronpedia

    INDEX
    Explanations

    Vf Control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    1.28
    can
    1.12
    ರ್
    1.01
    زی
    1.01
     the
    0.99
    glazed
    0.99
    LIN
    0.97
    RELATIVA
    0.96
    s
    0.95
    وی
    0.93
    POSITIVE LOGITS
    트
    1.13
    н
    1.11
    in
    1.07
    드
    1.03
    ն
    1.00
     bijz
    0.98
    ري
    0.97
    هاي
    0.97
     handel
    0.94
    什么
    0.93
    Act Density 0.000%

    No Known Activations