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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('='
    -0.07
    plementation
    -0.07
     Radar
    -0.06
    ього
    -0.06
    ITO
    -0.06
    .getText
    -0.06
    atisfaction
    -0.06
     l�
    -0.06
     |↵
    -0.06
    ，加
    -0.06
    POSITIVE LOGITS
    bris
    0.07
     shrugged
    0.07
     niet
    0.06
     خاطر
    0.06
    <GameObject
    0.06
    encrypt
    0.06
     poking
    0.06
    ↵				↵
    0.06
     pa
    0.06
     hired
    0.06
    Act Density 0.087%

    No Known Activations