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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulated
    -0.08
    すると
    -0.07
    >Edit
    -0.07
     purported
    -0.07
     confines
    -0.07
    -el
    -0.07
    Unused
    -0.07
     Libertarian
    -0.07
     militar
    -0.07
    处理
    -0.07
    POSITIVE LOGITS
     bä
    0.07
    	plt
    0.07
    PMC
    0.07
    çi
    0.06
    ạt
    0.06
     airl
    0.06
    (go
    0.06
     rng
    0.06
    lüğü
    0.06
    ält
    0.06
    Act Density 0.134%

    No Known Activations