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

    Neuronpedia

    INDEX
    Explanations

    understanding how something works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >').
    -0.08
    Remarks
    -0.08
    ]').
    -0.08
    eterminate
    -0.08
    ibu
    -0.07
     ചെയ്യുന്ന
    -0.07
     നടത്തുന്ന
    -0.07
     accommodates
    -0.07
     agencias
    -0.07
     Remarks
    -0.07
    POSITIVE LOGITS
    Understanding
    0.16
     Understanding
    0.15
    了解
    0.15
     understanding
    0.14
     తెలుస
    0.14
     поним
    0.14
     verstehen
    0.14
     kennen
    0.13
    掌
    0.13
    理解
    0.13
    Act Density 0.096%

    No Known Activations