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

    Neuronpedia

    INDEX
    Explanations

    ##

    np_max-act · gemini-2.0-flash

    The neuron flags Markdown‐style section headings (lines beginning with “##”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Jones
    -0.08
     Lig
    -0.07
     italic
    -0.07
    Zend
    -0.07
    -looking
    -0.07
     Jones
    -0.07
     glowing
    -0.07
     plug
    -0.07
     Logging
    -0.06
     fittings
    -0.06
    POSITIVE LOGITS
     ##
    0.10
    ##
    0.09
    rum
    0.08
    ##↵↵
    0.08
    ua
    0.07
    .pub
    0.07
     UNESCO
    0.07
     Cao
    0.07
    can
    0.07
     misconception
    0.07
    Act Density 0.005%

    No Known Activations