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

    Neuronpedia

    INDEX
    Explanations

    empty set axiom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     llave
    0.54
    seleccion
    0.52
    膣
    0.52
    គ
    0.51
    memberNameLink
    0.50
     कांसेप्ट
    0.50
     PartialEq
    0.49
    选手
    0.48
    )【
    0.47
    हल
    0.47
    POSITIVE LOGITS
     d
    0.59
    Graphs
    0.56
     jakie
    0.55
     D
    0.54
     Ná
    0.53
    ých
    0.53
     Æ
    0.52
    ę
    0.52
     dne
    0.52
     д
    0.51
    Act Density 0.007%

    No Known Activations