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

    Neuronpedia

    INDEX
    Explanations

    public class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    화
    0.67
    해주
    0.66
    hesi
    0.65
     estimés
    0.64
    KP
    0.62
    ul
    0.62
     হোমিও
    0.62
     ہار
    0.61
    লেম
    0.61
     Devin
    0.58
    POSITIVE LOGITS
     selfishness
    0.83
     selfish
    0.80
     exposes
    0.75
     spontaneous
    0.75
     implicit
    0.75
     nur
    0.75
     Implicit
    0.75
     involuntary
    0.75
    vout
    0.72
     spitting
    0.72
    Act Density 0.131%

    No Known Activations