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

    Neuronpedia

    INDEX
    Explanations

    Bench

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saved
    -0.07
    arity
    -0.06
    olders
    -0.06
    OA
    -0.06
    speed
    -0.06
    .ship
    -0.06
     진행
    -0.06
    ौल
    -0.06
     сор
    -0.06
     tří
    -0.06
    POSITIVE LOGITS
    Authorization
    0.07
    назнач
    0.07
     AutoMapper
    0.06
     architects
    0.06
    igraph
    0.06
    _rm
    0.06
     Dialogue
    0.06
    _listener
    0.06
    ?><?
    0.06
     neust
    0.06
    Act Density 0.000%

    No Known Activations