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

    Neuronpedia

    INDEX
    Explanations

    ube

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Support
    -0.06
     serializers
    -0.06
    enaire
    -0.06
     prevailing
    -0.06
     benef
    -0.06
    ombies
    -0.06
     인증
    -0.06
    %),
    -0.05
    Criteria
    -0.05
     Todo
    -0.05
    POSITIVE LOGITS
    __:
    0.07
    ór
    0.07
    kins
    0.07
    .ce
    0.07
     qed
    0.07
    374
    0.07
     cuc
    0.07
    Cap
    0.07
    藥
    0.07
     Bison
    0.07
    Act Density 0.001%

    No Known Activations