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

    Neuronpedia

    INDEX
    Explanations

    Data processing tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bha
    -0.08
     Vaj
    -0.08
    ‘l
    -0.08
     Brooke
    -0.08
     Sheng
    -0.08
     Cleveland
    -0.08
     Am
    -0.08
     Brides
    -0.08
     vaj
    -0.08
    ***/↵
    -0.07
    POSITIVE LOGITS
    leaf
    0.09
    Night
    0.09
     organically
    0.08
    worked
    0.08
    Intermediate
    0.08
    Organic
    0.08
     collaboratively
    0.08
    RUN
    0.08
    asmus
    0.08
    Leaf
    0.08
    Act Density 0.001%

    No Known Activations