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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breach
    -0.07
     než
    -0.07
    Predicate
    -0.06
     grows
    -0.06
     discovery
    -0.06
     preserves
    -0.06
     cuffs
    -0.06
    》的
    -0.06
     knot
    -0.06
     sandwiches
    -0.06
    POSITIVE LOGITS
    540
    0.07
    Ao
    0.07
    ("./
    0.06
     upstream
    0.06
    ри
    0.06
    utors
    0.06
    (dx
    0.06
     �
    0.06
    _span
    0.06
    .redis
    0.06
    Act Density 0.023%

    No Known Activations