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

    Neuronpedia

    INDEX
    Explanations

    bro split</response>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retweet
    0.76
    gib
    0.75
    Arial
    0.74
    orro
    0.72
    vii
    0.71
    আমি
    0.70
     elytra
    0.69
    ulty
    0.68
    ˇ
    0.68
     analy
    0.67
    POSITIVE LOGITS
    ować
    0.78
    是不
    0.71
     blancas
    0.70
     sejahtera
    0.70
     nantinya
    0.70
     જીવન
    0.69
     puede
    0.68
    ς
    0.67
     acompañ
    0.66
    収入
    0.66
    Act Density 0.001%

    No Known Activations