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

    Neuronpedia

    INDEX
    Explanations

    make decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ێنی
    1.27
     기간
    1.25
    දර
    1.20
     남자
    1.20
     반지름
    1.17
     못
    1.17
    ีก
    1.16
     posao
    1.16
     sektor
    1.15
    ஃப்
    1.14
    POSITIVE LOGITS
    iaus
    1.02
    will
    0.99
    icoes
    0.99
    imiento
    0.97
    对外
    0.96
     digress
    0.94
    ieke
    0.91
     परिवर्त
    0.90
     Cecil
    0.90
     Marl
    0.89
    Act Density 0.237%

    No Known Activations