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

    Neuronpedia

    INDEX
    Explanations

    INDIRECT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    },{↵
    -0.07
    -(
    -0.06
    UFACT
    -0.06
     marathon
    -0.06
     mates
    -0.06
     OPC
    -0.06
     중요한
    -0.06
    зв
    -0.06
    _logs
    -0.06
     Moff
    -0.06
    POSITIVE LOGITS
    reply
    0.08
    _slider
    0.07
    λύ
    0.07
    Liver
    0.07
    ْح
    0.06
    咲
    0.06
    indre
    0.06
    -aligned
    0.06
     Universities
    0.06
     Paige
    0.06
    Act Density 0.002%

    No Known Activations