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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кілька
    -0.07
    ленно
    -0.06
    および
    -0.06
     على
    -0.06
    Counter
    -0.06
    ETHER
    -0.06
     disparity
    -0.06
    _Runtime
    -0.06
     cualquier
    -0.06
    bounce
    -0.06
    POSITIVE LOGITS
     indispens
    0.07
    #aa
    0.07
     ide
    0.07
     ing
    0.07
    oundation
    0.06
     aVar
    0.06
    Serializer
    0.06
     injecting
    0.06
     a
    0.06
    ============
    0.06
    Act Density 0.025%

    No Known Activations