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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chess
    -0.06
     chí
    -0.06
     kolej
    -0.06
    へと
    -0.06
     Roland
    -0.06
    Post
    -0.06
     '^
    -0.06
     Mu
    -0.06
    Tab
    -0.06
    //---------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    quia
    0.07
     protections
    0.07
     realizing
    0.06
    ographic
    0.06
    selling
    0.06
     recognizable
    0.06
    قلال
    0.06
    ogne
    0.06
     demonstrate
    0.06
    努
    0.06
    Act Density 0.001%

    No Known Activations