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

    Neuronpedia

    INDEX
    Explanations

    roughly now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இவ்வ
    0.45
     ठिका
    0.44
    ciò
    0.44
    颞
    0.42
    źć
    0.42
     estés
    0.42
     இவ்
    0.42
     હું
    0.41
     Erschein
    0.41
    얘
    0.40
    POSITIVE LOGITS
    ophones
    0.40
     fundamental
    0.40
    ^{+}
    0.37
     published
    0.37
     drafted
    0.36
    olution
    0.36
     catalyst
    0.36
     estimated
    0.36
    ಿವೆ
    0.36
     officers
    0.36
    Act Density 0.001%

    No Known Activations