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

    Neuronpedia

    INDEX
    Explanations

    among or of followed by selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    0.76
    amless
    0.67
    cdot
    0.67
    fp
    0.64
    imen
    0.64
    ified
    0.64
    filled
    0.64
    েশনে
    0.64
    er
    0.63
    fal
    0.63
    POSITIVE LOGITS
     thoſe
    0.86
    ।,
    0.82
     những
    0.79
    三個
    0.79
     возможных
    0.78
     اینکه
    0.75
    śród
    0.74
     Kardashians
    0.73
     banyaknya
    0.73
     those
    0.72
    Act Density 0.025%

    No Known Activations