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

    Neuronpedia

    INDEX
    Explanations

    obligation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stagnant
    -0.07
     Champion
    -0.07
     approved
    -0.06
    Hyper
    -0.06
     httpClient
    -0.06
    _phase
    -0.06
     اختیار
    -0.06
     PROM
    -0.06
    _performance
    -0.06
     nắm
    -0.06
    POSITIVE LOGITS
    út
    0.08
    zeň
    0.07
     Nations
    0.07
    сім
    0.07
    ு
    0.06
    릭
    0.06
     tín
    0.06
    adora
    0.06
    ár
    0.06
    ρει
    0.06
    Act Density 0.013%

    No Known Activations