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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bos
    -0.07
     governors
    -0.07
     runaway
    -0.07
     �
    -0.06
    ('~
    -0.06
    Sentence
    -0.06
     Governors
    -0.06
     runway
    -0.06
    logue
    -0.06
     Mine
    -0.06
    POSITIVE LOGITS
     Rough
    0.07
     iddi
    0.06
     кош
    0.06
     CGContext
    0.06
     древ
    0.06
    method
    0.06
    уванні
    0.06
     nesting
    0.06
    ån
    0.06
    =pk
    0.06
    Act Density 0.020%

    No Known Activations