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

    Neuronpedia

    INDEX
    Explanations

    merkle branch, mountain, root

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nics
    1.22
    sers
    1.21
    at
    1.20
    nés
    1.20
    kult
    1.20
    rados
    1.16
    nahmen
    1.15
    nid
    1.13
    n
    1.13
    pour
    1.11
    POSITIVE LOGITS
    ü
    1.44
     i
    1.41
     can
    1.35
    0
    1.30
    ૦
    1.26
     as
    1.25
    ۰
    1.23
    ך
    1.20
     the
    1.18
    .
    1.18
    Act Density 0.000%

    No Known Activations