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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Including
    -0.54
    inflater
    -0.54
     אביב
    -0.52
     such
    -0.50
    PhysRevD
    -0.49
    such
    -0.49
    icoot
    -0.49
    Including
    -0.48
    isien
    -0.48
    囊
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.59
    NameInMap
    0.56
     nebo
    0.55
     eller
    0.54
     continúas
    0.53
     sœurs
    0.53
    rungsseite
    0.52
     indeb
    0.52
     مشين
    0.52
    OrFail
    0.50
    Act Density 0.000%

    No Known Activations