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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '})
    -0.07
     친구
    -0.06
     lived
    -0.06
     Stamp
    -0.06
    kin
    -0.06
    __);
    -0.06
     Such
    -0.06
     يجب
    -0.06
     stout
    -0.06
    ync
    -0.06
    POSITIVE LOGITS
    _office
    0.07
    TableWidgetItem
    0.07
    ishes
    0.06
    follower
    0.06
     Bayern
    0.06
     Pom
    0.06
    (constants
    0.06
     rulings
    0.06
    parseInt
    0.06
    _verified
    0.06
    Act Density 0.000%

    No Known Activations