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

    Neuronpedia

    INDEX
    Explanations

    rehabilitation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     museums
    -0.07
     avenues
    -0.07
     /=
    -0.07
    aldo
    -0.06
    ังจาก
    -0.06
     completo
    -0.06
     Barnes
    -0.06
    Iterable
    -0.06
     vendors
    -0.06
    itories
    -0.06
    POSITIVE LOGITS
    arence
    0.07
    	x
    0.07
    .setItems
    0.06
    ีข
    0.06
     InputDecoration
    0.06
    _corpus
    0.06
    638
    0.06
    _THE
    0.06
     платеж
    0.06
     mes
    0.06
    Act Density 0.050%

    No Known Activations