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

    Neuronpedia

    INDEX
    Explanations

    Error Handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    evice
    0.38
    ખ્ય
    0.38
    ರಣ
    0.38
    empirical
    0.37
    ீரல்
    0.37
    evaluate
    0.36
     लिखे
    0.36
    eacute
    0.36
    aksanakan
    0.36
     проблемы
    0.36
    POSITIVE LOGITS
     prevention
    0.75
     handling
    0.73
     handing
    0.73
    Handling
    0.70
     Handling
    0.69
    Hand
    0.67
    HAND
    0.67
    ハンド
    0.66
     hand
    0.66
     trapping
    0.65
    Act Density 0.036%

    No Known Activations