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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＿__
    -0.07
    ramento
    -0.07
    ContentType
    -0.06
    Standard
    -0.06
     Assign
    -0.06
     rozší
    -0.06
    Judge
    -0.06
    anya
    -0.06
    okol
    -0.06
    Title
    -0.06
    POSITIVE LOGITS
     нему
    0.08
     fiberglass
    0.07
    Ont
    0.07
     ευ
    0.07
     Neural
    0.07
     сок
    0.07
     FirebaseAuth
    0.06
    尤
    0.06
    taş
    0.06
     Dakota
    0.06
    Act Density 0.024%

    No Known Activations