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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .variables
    -0.07
     '**
    -0.06
     conceived
    -0.06
    oter
    -0.06
    bies
    -0.06
     zak
    -0.06
     performs
    -0.06
     isError
    -0.06
    ’da
    -0.06
     persona
    -0.06
    POSITIVE LOGITS
    ConfigurationException
    0.07
    ником
    0.07
    (response
    0.07
    есп
    0.06
    期待
    0.06
     impending
    0.06
    _quantity
    0.06
     unrestricted
    0.06
    ody
    0.06
    .text
    0.06
    Act Density 0.009%

    No Known Activations