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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mal
    -0.07
    acity
    -0.07
    เล
    -0.06
    浴
    -0.06
    rieb
    -0.06
    =ax
    -0.06
    步
    -0.06
    lia
    -0.06
     교수
    -0.06
     द
    -0.06
    POSITIVE LOGITS
     každ
    0.06
     garnered
    0.06
    --
    0.06
    (phone
    0.06
    lesi
    0.06
    aaa
    0.06
     traveler
    0.06
    (ii
    0.06
     martin
    0.06
    Ay
    0.06
    Act Density 0.000%

    No Known Activations