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

    Neuronpedia

    INDEX
    Explanations

    can cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LP
    0.39
     antennis
    0.39
    ការព
    0.38
    ăș
    0.38
    👼
    0.38
     LP
    0.38
     Aank
    0.38
     స్థితి
    0.36
    apag
    0.36
    utian
    0.36
    POSITIVE LOGITS
     গভ
    0.39
     comen
    0.38
     leech
    0.38
     ref
    0.37
     majority
    0.37
     release
    0.36
    forced
    0.36
     mayoría
    0.36
     emergency
    0.36
    めた
    0.35
    Act Density 0.001%

    No Known Activations