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

    Neuronpedia

    INDEX
    Explanations

    chemical formulas and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𐰚
    0.58
     devaluation
    0.55
    权力
    0.55
    逦
    0.54
    珢
    0.54
    <unused265>
    0.54
    㑔
    0.54
    聝
    0.54
    上涨
    0.53
    浈
    0.53
    POSITIVE LOGITS
     salts
    0.70
    min
    0.63
     O
    0.63
    ate
    0.63
    0.62
    bl
    0.61
    3
    0.61
    ide
    0.59
    O
    0.59
    I
    0.59
    Act Density 0.011%

    No Known Activations