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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the identifier “name” (e.g. property or parameter named “name”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     doctrines
    -0.06
     ballistic
    -0.06
     […]
    -0.06
    fresh
    -0.06
    -outs
    -0.06
     Algebra
    -0.06
     algebra
    -0.06
    	re
    -0.06
     Munich
    -0.06
    amma
    -0.06
    POSITIVE LOGITS
    ysqli
    0.07
    -custom
    0.07
    .alias
    0.07
     Xxx
    0.07
    gue
    0.06
    CLUD
    0.06
    ughter
    0.06
     onze
    0.06
    dens
    0.06
    .shadow
    0.06
    Act Density 0.103%

    No Known Activations