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

    Neuronpedia

    INDEX
    Explanations

    technical discussion or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瑭
    0.52
    voorbeeld
    0.46
    見
    0.43
    英文
    0.42
    娜
    0.42
     между
    0.42
    ところが
    0.42
    田
    0.41
    정을
    0.41
    湯
    0.41
    POSITIVE LOGITS
     pož
    0.54
     zeal
    0.52
     heinous
    0.51
     aye
    0.49
     perpetuated
    0.48
     vě
    0.48
     propagand
    0.48
    jobSize
    0.47
    Company
    0.46
     opted
    0.46
    Act Density 0.001%

    No Known Activations