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

    Neuronpedia

    INDEX
    Explanations

    comma followed by real

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Real
    0.63
     реа
    0.57
    REAL
    0.54
    real
    0.52
     Real
    0.52
     real
    0.52
     REAL
    0.47
    кер
    0.42
    реа
    0.42
     रियल
    0.41
    POSITIVE LOGITS
     Griffith
    0.40
     Griff
    0.39
    随时
    0.37
    持つ
    0.36
    不错
    0.36
     Plots
    0.35
     ঘরে
    0.35
     Panda
    0.35
    ness
    0.35
    फ़
    0.34
    Act Density 0.001%

    No Known Activations