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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    İL
    -0.07
    LB
    -0.07
    』
    -0.07
     WL
    -0.07
     ל
    -0.07
    (DE
    -0.06
    DECLARE
    -0.06
    _REFRESH
    -0.06
    OLD
    -0.06
    PERTIES
    -0.06
    POSITIVE LOGITS
    _users
    0.07
     использов
    0.06
    vas
    0.06
     legislation
    0.06
    Oct
    0.06
    ρκεια
    0.06
     nhóm
    0.06
     handsome
    0.06
     India
    0.06
    _par
    0.06
    Act Density 0.008%

    No Known Activations