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

    Neuronpedia

    INDEX
    Explanations

    famous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “When
    -0.08
    "When
    -0.07
    “And
    -0.07
     Jul
    -0.07
    “How
    -0.06
    controls
    -0.06
     Workflow
    -0.06
    <l
    -0.06
    ιακ
    -0.06
    	where
    -0.06
    POSITIVE LOGITS
     famous
    0.10
     Famous
    0.08
    -known
    0.07
    風
    0.07
    ￣￣￣
    0.07
     infamous
    0.07
     herald
    0.06
     Associated
    0.06
     Tel
    0.06
    /report
    0.06
    Act Density 0.017%

    No Known Activations