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

    Neuronpedia

    INDEX
    Explanations

    behavior of values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cri
    0.44
     cri
    0.41
     tensión
    0.41
    Thickness
    0.40
    POV
    0.39
    cave
    0.39
    υχ
    0.39
    ージー
    0.39
     omnis
    0.37
     Cri
    0.37
    POSITIVE LOGITS
    WIDE
    0.41
     Azul
    0.39
    *((
    0.37
     CST
    0.37
     stars
    0.36
     smart
    0.36
     Humboldt
    0.36
     followers
    0.35
     সাল
    0.35
    Rt
    0.35
    Act Density 0.001%

    No Known Activations