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

    Neuronpedia

    INDEX
    Explanations

    chemical stoff name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.70
    et
    0.63
    ie
    0.62
    o
    0.59
    es
    0.58
    ap
    0.57
    و
    0.57
     م
    0.54
    oh
    0.54
    ed
    0.53
    POSITIVE LOGITS
     antitrust
    0.52
     decarbon
    0.48
     stargazerCount
    0.46
     unwillingness
    0.46
    <0xD0>
    0.46
    PastPositions
    0.45
     unavoid
    0.44
     заработной
    0.44
    də
    0.44
     جوسینو
    0.44
    Act Density 0.000%

    No Known Activations