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

    Neuronpedia

    INDEX
    Explanations

    sailed away, however, needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bringing
    0.42
    <0xCE>
    0.41
     servidor
    0.41
     మాత్రం
    0.41
     अम
    0.39
     Brought
    0.39
     Слу
    0.38
     seldom
    0.38
     ያስ
    0.38
    uttore
    0.38
    POSITIVE LOGITS
    磧
    0.46
    ROWS
    0.44
    рена
    0.42
    딨
    0.42
    patch
    0.41
    Nas
    0.41
     prist
    0.41
     patches
    0.40
    騏
    0.40
     mosaics
    0.40
    Act Density 0.000%

    No Known Activations