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
     tor
    -0.06
    .light
    -0.06
    .blank
    -0.06
    效果
    -0.06
    (stream
    -0.06
    acts
    -0.06
     wit
    -0.06
     revealed
    -0.06
    (in
    -0.06
    TimeStamp
    -0.05
    POSITIVE LOGITS
    _embeddings
    0.07
    _BACKEND
    0.07
    	   ↵
    0.07
    πέ
    0.07
    .Ret
    0.07
     ورز
    0.06
    �
    0.06
    Fant
    0.06
     cuck
    0.06
     없어
    0.06
    Act Density 0.007%

    No Known Activations