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

    Neuronpedia

    INDEX
    Explanations

    Unstructured data/non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MOD
    -0.08
     заст
    -0.08
    ास्त
    -0.08
     largely
    -0.08
    _FLASH
    -0.08
     ضغط
    -0.08
     posterior
    -0.08
    _BAL
    -0.07
     عليها
    -0.07
     ausgesch
    -0.07
    POSITIVE LOGITS
     warehouses
    0.08
     kell
    0.08
     Virginia
    0.08
     traps
    0.08
    CCR
    0.08
     vir
    0.08
    'art
    0.07
     dwe
    0.07
     hubs
    0.07
    Virginia
    0.07
    Act Density 0.001%

    No Known Activations