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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _text
    -0.06
    .geom
    -0.06
    :'
    -0.06
    ={['
    -0.06
    [word
    -0.06
     describing
    -0.06
    acf
    -0.06
    	debug
    -0.05
    -support
    -0.05
    люд
    -0.05
    POSITIVE LOGITS
    ())↵↵↵
    0.08
    ')↵↵↵
    0.08
    >();
↵
↵
    0.07
    =");↵
    0.07
     istediğiniz
    0.07
     })();↵
    0.07
    ());↵↵↵
    0.07
    ));↵↵↵
    0.07
    ↵↵↵↵
    0.07
     ]↵↵↵
    0.07
    Act Density 0.114%

    No Known Activations