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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dau
    -0.07
    postgres
    -0.06
     underneath
    -0.06
    Reducer
    -0.06
     upside
    -0.06
     supreme
    -0.06
    tra
    -0.06
    adj
    -0.06
     UC
    -0.06
     iterable
    -0.06
    POSITIVE LOGITS
    .
    0.07
     Peggy
    0.07
     Morrison
    0.06
     budeme
    0.06
     EUR
    0.06
     yang
    0.06
    vement
    0.06
    أت
    0.06
    TECT
    0.06
    /↵
    0.06
    Act Density 0.000%

    No Known Activations