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

    Neuronpedia

    INDEX
    Explanations

    true or false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ducks
    -0.07
    $output
    -0.07
    Pal
    -0.06
     duck
    -0.06
    ังส
    -0.06
     manufact
    -0.06
    �
    -0.06
    oystick
    -0.06
     ridden
    -0.06
     honorary
    -0.06
    POSITIVE LOGITS
    σία
    0.07
    ılığ
    0.07
    kiem
    0.07
     Firestore
    0.06
    ANC
    0.06
     إلا
    0.06
     langue
    0.06
    ظام
    0.06
    －
    0.06
    .double
    0.06
    Act Density 0.010%

    No Known Activations