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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OF
    -0.07
    _agents
    -0.07
    >).
    -0.06
     ند
    -0.06
     oblig
    -0.06
    unar
    -0.06
     روند
    -0.06
    跟
    -0.06
     };
↵
    -0.06
     scrolling
    -0.06
    POSITIVE LOGITS
    idir
    0.07
     Mitt
    0.07
    Screenshot
    0.06
    bay
    0.06
    duto
    0.06
    _relative
    0.06
    	api
    0.06
    agonal
    0.06
    _MB
    0.06
    serrat
    0.06
    Act Density 0.001%

    No Known Activations