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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心得
    0.77
     ಬಗ್ಗೆ
    0.71
    mania
    0.65
    道歉
    0.62
     に関
    0.62
     markdown
    0.61
    をや
    0.61
    hebung
    0.60
    ^+
    0.60
    iophorus
    0.59
    POSITIVE LOGITS
    లోని
    1.20
    ంలోని
    1.11
    các
    0.90
     các
    0.84
    中の
    0.83
    ത്തിലെ
    0.82
    ிலுள்ள
    0.81
    дің
    0.81
     socalled
    0.80
    }}{
    0.79
    Act Density 0.501%

    No Known Activations