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

    Neuronpedia

    INDEX
    Explanations

    zero and percentages

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any of the content—it never activates on any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Anaheim
    -0.07
    Debugger
    -0.07
     Malta
    -0.06
     Diagram
    -0.06
    Advanced
    -0.06
     Sala
    -0.06
    507
    -0.06
     выдел
    -0.06
     dissolved
    -0.06
    422
    -0.06
    POSITIVE LOGITS
     <!--<
    0.07
    (graph
    0.07
    *r
    0.06
    ountries
    0.06
    (TokenType
    0.06
     ft
    0.06
     Iterator
    0.06
    $url
    0.06
    [idx
    0.06
     casualties
    0.06
    Act Density 0.016%

    No Known Activations