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

    Neuronpedia

    INDEX
    Explanations

    Code and numbers

    np_max-act · gemini-2.0-flash

    Detects the special NAME_ placeholder token used to mark character/entity identifiers.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .mapbox
    -0.08
    狒
    -0.08
    KeyListener
    -0.07
    _logits
    -0.07
    Interpolator
    -0.07
    .rmi
    -0.07
    indi
    -0.07
    .ip
    -0.07
     Lamp
    -0.07
     though
    -0.07
    POSITIVE LOGITS
    sehen
    0.08
     Templ
    0.08
     sider
    0.07
    ções
    0.07
     !=↵
    0.07
     FRE
    0.07
    če
    0.07
    籍
    0.07
     déco
    0.07
    Pwd
    0.07
    Act Density 0.066%

    No Known Activations