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

    Neuronpedia

    INDEX
    Explanations

    print type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RECENT
    0.39
     Farley
    0.38
    ၜ
    0.38
    জনাব
    0.38
    GLIGENCE
    0.37
    Slack
    0.37
    Recently
    0.36
    Regulation
    0.35
    ону
    0.35
    をお願い
    0.35
    POSITIVE LOGITS
     type
    1.09
    type
    0.94
     typeof
    0.84
    typeof
    0.77
     tipo
    0.73
     getType
    0.68
     TYPE
    0.66
     isinstance
    0.65
     типу
    0.65
     typu
    0.64
    Act Density 0.011%

    No Known Activations