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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frances
    -0.08
    ASTER
    -0.07
     Exercise
    -0.07
    -running
    -0.06
     американ
    -0.06
     elephant
    -0.06
    iores
    -0.06
    خف
    -0.06
     Be
    -0.06
    (I
    -0.06
    POSITIVE LOGITS
    -cart
    0.07
    '];?>↵
    0.07
    여
    0.06
    labs
    0.06
     Managed
    0.06
    ilyn
    0.06
    :".
    0.06
    _sdk
    0.06
    )}}
    0.06
    ;}
    0.06
    Act Density 0.003%

    No Known Activations