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

    Neuronpedia

    INDEX
    Explanations

    cocoa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paren
    -0.08
    	unset
    -0.06
    igner
    -0.06
     BOOLEAN
    -0.06
    Na
    -0.06
    (ch
    -0.06
    нять
    -0.06
     exhibitions
    -0.06
    翻
    -0.06
    taient
    -0.06
    POSITIVE LOGITS
     cocoa
    0.12
     Sea
    0.07
     Cocoa
    0.07
     broadly
    0.07
     Bishop
    0.06
     hoses
    0.06
    };↵↵↵
    0.06
    ocoa
    0.06
     chemicals
    0.06
    Prom
    0.06
    Act Density 0.001%

    No Known Activations