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

    Neuronpedia

    INDEX
    Explanations

    pain or truth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.48
    子の
    0.44
     Ice
    0.41
    esian
    0.41
    以下の
    0.39
     Textile
    0.39
    mute
    0.39
     Theories
    0.39
     Textiles
    0.39
     Lake
    0.38
    POSITIVE LOGITS
     BECAUSE
    0.42
    গুরু
    0.40
    INCT
    0.40
     רא
    0.40
     прису
    0.40
     че
    0.39
    령
    0.38
    CHECKS
    0.38
     විශ
    0.38
    驃
    0.38
    Act Density 0.004%

    No Known Activations