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

    Neuronpedia

    INDEX
    Explanations

    hint at suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एकूण
    0.52
     kautta
    0.47
    ziná
    0.44
    闺
    0.44
     Така
    0.43
    geny
    0.43
     Джон
    0.43
    ifera
    0.42
     autént
    0.42
     нюан
    0.42
    POSITIVE LOGITS
     govern
    0.42
    IL
    0.41
    Rename
    0.39
    )",
    0.38
    Callable
    0.37
     Hale
    0.36
     desirable
    0.36
     rename
    0.36
    CSA
    0.36
    যাপন
    0.36
    Act Density 0.001%

    No Known Activations