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
     Id
    -0.06
    proof
    -0.06
     '.')
    -0.06
     Serie
    -0.06
     cruiser
    -0.06
    ,o
    -0.06
     nh
    -0.06
     gid
    -0.06
     remove
    -0.05
     nonlinear
    -0.05
    POSITIVE LOGITS
    .getDate
    0.07
    (Long
    0.07
    αρα
    0.07
    然而
    0.07
    征
    0.06
    	Method
    0.06
    ентов
    0.06
     امید
    0.06
    ctrine
    0.06
    enate
    0.06
    Act Density 0.032%

    No Known Activations