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

    Neuronpedia

    INDEX
    Explanations

    basic building blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     envis
    1.46
     TID
    1.44
     madam
    1.40
    ッド
    1.40
     Ched
    1.40
     (’
    1.40
    idated
    1.39
    çons
    1.37
     coder
    1.36
    ouncement
    1.33
    POSITIVE LOGITS
    \
    1.18
     \
    1.04
    rinsic
    0.95
    ເຊ
    0.86
     precipit
    0.85
     personnelles
    0.84
    6
    0.84
    8
    0.82
     monstru
    0.82
    ازه
    0.81
    Act Density 0.030%

    No Known Activations