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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     each
    -0.08
     관리
    -0.07
     seper
    -0.07
    मन
    -0.07
     jede
    -0.06
    1
    -0.06
    ()],↵
    -0.06
    -orange
    -0.06
     one
    -0.06
     former
    -0.06
    POSITIVE LOGITS
     BaseModel
    0.06
    .assertNot
    0.06
    embedded
    0.06
    ???
    0.06
    progress
    0.06
    (KERN
    0.06
    _dump
    0.06
    ).'
    0.06
    _logged
    0.06
    createFrom
    0.06
    Act Density 0.184%

    No Known Activations