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

    Neuronpedia

    INDEX
    Explanations

    factual statements and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pivoting
    0.42
     보호
    0.40
     pivot
    0.39
     echoed
    0.39
    code
    0.38
    목
    0.38
    agm
    0.37
    控制
    0.37
     Perf
    0.36
     hidden
    0.36
    POSITIVE LOGITS
     facts
    0.42
     factual
    0.40
    ニコ
    0.40
     bonds
    0.39
     disband
    0.39
     член
    0.39
     whereby
    0.38
     friendships
    0.38
     chieft
    0.38
    ཱ
    0.38
    Act Density 0.001%

    No Known Activations