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

    Neuronpedia

    INDEX
    Explanations

    return 0;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.56
    ्य
    0.50
    Y
    0.47
    я
    0.47
    1
    0.46
    ível
    0.46
    ный
    0.45
     umíst
    0.44
     tijd
    0.44
    4
    0.44
    POSITIVE LOGITS
    ar
    0.61
    is
    0.48
     Dialogue
    0.48
    瑁
    0.48
    ad
    0.47
    esthetic
    0.47
    derived
    0.46
     MCSF
    0.45
    ot
    0.45
    sens
    0.44
    Act Density 0.041%

    No Known Activations