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

    Neuronpedia

    INDEX
    Explanations

    code/set theory/lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vil
    -0.07
     gir
    -0.07
    <Test
    -0.07
    转向
    -0.07
     carga
    -0.06
    _Default
    -0.06
    Spain
    -0.06
     Sof
    -0.06
    	target
    -0.06
     Understand
    -0.06
    POSITIVE LOGITS
    琊
    0.08
    leting
    0.07
     embeddings
    0.07
     commemor
    0.07
    utches
    0.07
     watermark
    0.07
    .method
    0.07
    .strftime
    0.07
    Comments
    0.07
    -Star
    0.07
    Act Density 0.009%

    No Known Activations