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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mid
    -5.34
    mid
    -4.19
    Mid
    -3.67
     Mid
    -3.38
    MID
    -2.98
     MID
    -2.75
     mids
    -2.44
     midpoint
    -2.16
    中
    -2.13
     mida
    -2.09
    POSITIVE LOGITS
    ˩
    0.82
    Bande
    0.71
    bandera
    0.71
    folia
    0.66
     Moderna
    0.66
    ettet
    0.65
    hn
    0.65
     Njema
    0.65
    stasi
    0.64
    Layered
    0.64
    Act Density 0.089%

    No Known Activations