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

    Neuronpedia

    INDEX
    Explanations

    MATLAB and coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    notice
    -0.08
    achine
    -0.07
     Machines
    -0.06
     Machine
    -0.06
    ector
    -0.06
     sudden
    -0.06
    snake
    -0.06
    within
    -0.06
    Snake
    -0.06
    appointment
    -0.06
    POSITIVE LOGITS
     интерес
    0.07
    �
    0.06
    .author
    0.06
    ��
    0.06
     cre
    0.06
     screenHeight
    0.06
     Influ
    0.06
    γραφ
    0.06
     Praha
    0.06
    �장
    0.06
    Act Density 0.024%

    No Known Activations