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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tut
    -0.07
     EIF
    -0.07
    拟定
    -0.07
    ridged
    -0.06
    vect
    -0.06
     Decay
    -0.06
    /go
    -0.06
    gmt
    -0.06
    \xff
    -0.06
    ôtel
    -0.06
    POSITIVE LOGITS
    失业
    0.07
    						↵
    0.07
    �
    0.07
    *k
    0.07
    ]):↵
    0.07
    □
    0.07
    };↵↵
    0.07
     };↵↵↵
    0.06
    效益
    0.06
     baseline
    0.06
    Act Density 0.022%

    No Known Activations