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

    Neuronpedia

    INDEX
    Explanations

    basement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Africa
    -0.06
    (weight
    -0.06
     sealing
    -0.06
     Maurit
    -0.06
    кую
    -0.06
     excit
    -0.06
    -level
    -0.06
    ，最
    -0.06
    iji
    -0.06
     Fi
    -0.06
    POSITIVE LOGITS
     dois
    0.07
    "...
    0.07
    "=>"
    0.07
     такого
    0.07
     Nicholas
    0.06
    xlsx
    0.06
    "]).
    0.06
     investigating
    0.06
    ']}
    0.06
     OC
    0.06
    Act Density 0.004%

    No Known Activations