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

    Neuronpedia

    INDEX
    Explanations

    Common sentence structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Booker
    -0.07
    TY
    -0.07
     Ding
    -0.06
    �
    -0.06
     BM
    -0.06
    predicate
    -0.06
     tvá
    -0.06
     Duplicate
    -0.06
    ระหว
    -0.06
     theo
    -0.06
    POSITIVE LOGITS
    __/
    0.07
    moduleId
    0.07
    oothing
    0.06
    .Kind
    0.06
    ~~~~
    0.06
    eft
    0.06
     disrespect
    0.06
    _ss
    0.06
     );
↵
↵
    0.06
    unga
    0.06
    Act Density 0.071%

    No Known Activations