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

    Neuronpedia

    INDEX
    Explanations

    no selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     republished
    0.40
    RetResult
    0.39
    nancy
    0.38
     mío
    0.38
    जफ्
    0.37
     بیټ
    0.37
    atthena
    0.37
     previewBuilder
    0.37
     PREMIUM
    0.37
    ogramDetails
    0.36
    POSITIVE LOGITS
     We
    0.39
     Addition
    0.39
    する場合
    0.38
    ・
    0.38
    -
    0.38
     Whereas
    0.38
    하고
    0.37
     Honors
    0.37
     The
    0.35
    着的
    0.35
    Act Density 0.001%

    No Known Activations