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

    Neuronpedia

    INDEX
    Explanations

    technical reports, numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compare
    -0.07
    教师
    -0.07
    ]');↵
    -0.07
     sharper
    -0.06
    AAC
    -0.06
     Lever
    -0.06
     isNaN
    -0.06
    -unused
    -0.06
     。
    -0.06
     이것
    -0.06
    POSITIVE LOGITS
     стати
    0.07
    (up
    0.07
    (system
    0.07
     Kings
    0.07
     flirt
    0.06
    /questions
    0.06
    uş
    0.06
    ovel
    0.06
     Up
    0.06
    out
    0.06
    Act Density 12.608%

    No Known Activations