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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divide
    -0.06
    Numeric
    -0.06
     Ric
    -0.06
    .Inf
    -0.06
     contiene
    -0.06
     Patent
    -0.06
    addy
    -0.06
    .HorizontalAlignment
    -0.06
    @Override
    -0.06
     rematch
    -0.05
    POSITIVE LOGITS
    _form
    0.07
    _frag
    0.07
    選
    0.07
     กล
    0.07
     extras
    0.07
     Goodman
    0.07
    认识
    0.06
    (q
    0.06
    unday
    0.06
     catastrophe
    0.06
    Act Density 0.001%

    No Known Activations