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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	lua
    -0.08
    人们
    -0.07
    Like
    -0.07
     δεν
    -0.06
    発表
    -0.06
    華
    -0.06
    (dom
    -0.06
    207
    -0.06
     درآمد
    -0.06
     Αρ
    -0.06
    POSITIVE LOGITS
    arbonate
    0.06
    укт
    0.06
    .clips
    0.06
    lan
    0.06
     Pipeline
    0.06
    pf
    0.06
        
    0.06
    �
    0.05
    .any
    0.05
    .Tipo
    0.05
    Act Density 0.010%

    No Known Activations