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

    Neuronpedia

    INDEX
    Explanations

    typical breakup excuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Proceed
    0.38
     تعريف
    0.38
    ]})
    0.37
    Morph
    0.37
    𝗿
    0.37
     proceed
    0.36
    ್ಟ
    0.36
     proceeds
    0.36
    ণিক
    0.35
     Proceeds
    0.35
    POSITIVE LOGITS
     externo
    0.42
     olmuş
    0.41
    很难
    0.39
     ja
    0.39
     within
    0.38
     externes
    0.38
     correctly
    0.38
     logging
    0.38
    灭
    0.38
    已经
    0.38
    Act Density 0.000%

    No Known Activations