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

    Neuronpedia

    INDEX
    Explanations

    was written

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oaks
    -0.11
     Chap
    -0.10
    achen
    -0.10
    ãĥ«ãĥĪ
    -0.10
    uster
    -0.09
    akin
    -0.09
     丶
    -0.09
    447
    -0.09
    671
    -0.08
    /--
    -0.08
    POSITIVE LOGITS
     çĶ±
    0.18
    çĶ±
    0.18
     zosta
    0.15
     was
    0.15
     fue
    0.13
     foi
    0.12
     were
    0.12
     fueron
    0.12
     wurde
    0.12
    å½Ĵ
    0.12
    Act Density 0.178%

    No Known Activations