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

    Neuronpedia

    INDEX
    Explanations

    states of being, subjects of concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMENTO
    0.49
    义
    0.46
    seamless
    0.46
    なんと
    0.44
    Quién
    0.42
    rát
    0.42
    ionato
    0.41
    benzoyl
    0.41
    ANNEL
    0.40
    unen
    0.40
    POSITIVE LOGITS
    《
    0.42
     。,
    0.42
     प्लीज
    0.42
    |}\
    0.41
     Everyday
    0.40
    螺
    0.39
     Please
    0.37
    婴
    0.36
    denom
    0.36
     《
    0.35
    Act Density 0.000%

    No Known Activations