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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -operation
    -0.07
     kterého
    -0.07
    ोष
    -0.07
    την
    -0.07
     hodnot
    -0.06
    moved
    -0.06
     Quando
    -0.06
    apanese
    -0.06
     internals
    -0.06
    cm
    -0.06
    POSITIVE LOGITS
    Target
    0.06
     duck
    0.06
    <Course
    0.06
    ltk
    0.06
    .uri
    0.06
    asuring
    0.06
    	Intent
    0.06
    _stack
    0.06
    ayar
    0.06
    gements
    0.06
    Act Density 0.067%

    No Known Activations