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

    Neuronpedia

    INDEX
    Explanations

    direction and internal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orse
    0.56
    ugi
    0.54
    iru
    0.52
    uen
    0.51
    uru
    0.50
    uk
    0.48
    ud
    0.48
    oulders
    0.48
    usive
    0.47
    rou
    0.47
    POSITIVE LOGITS
    Knife
    0.50
    ঠাৎ
    0.49
    য়ের
    0.49
     Фурга
    0.46
     contin
    0.46
    Transcript
    0.46
     xas
    0.46
     aperta
    0.46
     envi
    0.45
     Anchorage
    0.45
    Act Density 0.000%

    No Known Activations