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

    Neuronpedia

    INDEX
    Explanations

    Movement, Speed, conquer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    align
    0.68
    aligned
    0.63
     aligned
    0.60
     alignment
    0.57
    alignment
    0.55
    Aligned
    0.54
    Align
    0.52
     align
    0.51
     alignments
    0.50
     Alignment
    0.50
    POSITIVE LOGITS
     llc
    0.45
     capazes
    0.42
    пут
    0.40
     procession
    0.39
     PHYSI
    0.39
     erleben
    0.39
     interceptions
    0.38
    мян
    0.38
    бля
    0.38
    ائیو
    0.38
    Act Density 0.000%

    No Known Activations