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
    �
    -0.07
    imator
    -0.07
     elektron
    -0.06
    .INFO
    -0.06
    lige
    -0.06
     kvinner
    -0.06
    105
    -0.06
     tj
    -0.06
    26
    -0.06
     fit
    -0.06
    POSITIVE LOGITS
     Jays
    0.06
     Flem
    0.06
     гум
    0.06
     hast
    0.06
     Vive
    0.06
    !!!↵↵
    0.06
    ="'.$
    0.06
    ding
    0.06
     Mush
    0.06
     ---------------------------------------------------------------------------↵
    0.06
    Act Density 0.010%

    No Known Activations