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

    Neuronpedia

    INDEX
    Explanations

    Show me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aloud
    0.79
    eses
    0.79
     이야기
    0.77
     Unable
    0.75
     DIFFIC
    0.73
     occurred
    0.72
    ङ
    0.71
     opinions
    0.70
     opinion
    0.69
     about
    0.68
    POSITIVE LOGITS
    すべての
    1.02
     wszystkich
    0.92
     stöd
    0.89
    AllWindows
    0.84
    及ひ
    0.82
     všech
    0.81
     semua
    0.81
    Paths
    0.81
    表記
    0.81
    全ての
    0.81
    Act Density 0.010%

    No Known Activations