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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kı
    -0.07
     Beth
    -0.07
    awaiter
    -0.06
     negate
    -0.06
     YYSTYPE
    -0.06
     Κου
    -0.06
    _dropout
    -0.06
     دقی
    -0.06
    .initState
    -0.06
     aeros
    -0.06
    POSITIVE LOGITS
     understood
    0.10
     understand
    0.09
     understands
    0.07
     perceive
    0.07
     навч
    0.07
     Understand
    0.07
     Arlington
    0.07
     perceived
    0.06
    /Auth
    0.06
    <i
    0.06
    Act Density 0.032%

    No Known Activations