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

    Neuronpedia

    INDEX
    Explanations

    listing first items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     http
    0.44
     λόγω
    0.41
     médical
    0.41
    Sph
    0.40
    http
    0.40
     využ
    0.39
    -
    0.38
    wijl
    0.36
     díky
    0.36
    Rare
    0.35
    POSITIVE LOGITS
     firstly
    0.57
     two
    0.52
     primero
    0.48
     primeiro
    0.46
     сначала
    0.46
     firstname
    0.46
     przede
    0.46
     onSubmit
    0.46
     然后
    0.46
     Pattaya
    0.46
    Act Density 0.012%

    No Known Activations