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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    block
    -0.07
     blunt
    -0.07
     rock
    -0.06
     selling
    -0.06
     believes
    -0.06
     '↵
    -0.06
     perpetrators
    -0.06
     },
    -0.06
     correction
    -0.06
    .update
    -0.06
    POSITIVE LOGITS
    Local
    0.07
    _CUDA
    0.06
     Erot
    0.06
     возника
    0.06
     Sasha
    0.06
     BBQ
    0.06
    igeria
    0.06
     Suddenly
    0.06
     немного
    0.06
     timid
    0.06
    Act Density 0.105%

    No Known Activations