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

    Neuronpedia

    INDEX
    Explanations

    Colab, Registry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    2.05
    lm
    1.41
    L
    1.40
    le
    1.36
    lı
    1.35
    Л
    1.34
    lés
    1.33
    lers
    1.32
    ל
    1.32
    ل
    1.31
    POSITIVE LOGITS
    Cay
    1.29
     Warwick
    1.08
    asan
    1.01
     Couch
    0.98
    achten
    0.97
     Abbas
    0.94
    ased
    0.94
    carbons
    0.93
     spore
    0.93
     teinture
    0.92
    Act Density 0.425%

    No Known Activations