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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atever
    -0.06
     candidate
    -0.06
     approval
    -0.06
    .GREEN
    -0.06
     deputy
    -0.06
    xx
    -0.06
    bearing
    -0.06
     weekend
    -0.06
    "><?=
    -0.06
    ोफ
    -0.06
    POSITIVE LOGITS
    ＞
    0.07
     CAS
    0.07
     zun
    0.07
    (pin
    0.07
     ({
    0.06
    ğimiz
    0.06
     дост
    0.06
    ��
    0.06
    'utilisateur
    0.06
     الرو
    0.06
    Act Density 0.023%

    No Known Activations