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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to URL path components—especially slashes and “documentation”/“reference” segments—in API or docs links.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Came
    -0.07
    ляли
    -0.07
    {s
    -0.06
    	parent
    -0.06
     deposit
    -0.06
     fet
    -0.06
    _authentication
    -0.06
     valida
    -0.06
    rename
    -0.06
     strany
    -0.06
    POSITIVE LOGITS
     cho
    0.07
    ,re
    0.06
    0.06
     @
    0.06
    CKER
    0.06
    >:
    0.06
    .ListBox
    0.06
    :`
    0.06
    /
    0.06
    lycer
    0.06
    Act Density 0.038%

    No Known Activations