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

    Neuronpedia

    INDEX
    Explanations

    Filler words

    np_max-act · gemini-2.0-flash

    The neuron never activates—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ITER
    -0.06
    iliate
    -0.06
     TVs
    -0.06
    Guy
    -0.06
     hers
    -0.06
     erfolgre
    -0.06
    dın
    -0.06
    ZN
    -0.06
     heute
    -0.06
    Shop
    -0.06
    POSITIVE LOGITS
    -groups
    0.07
     };
↵
    0.07
    .ant
    0.07
    /themes
    0.06
     گروه
    0.06
    แท
    0.06
     standout
    0.06
    _CART
    0.06
     З
    0.06
    ima
    0.06
    Act Density 0.020%

    No Known Activations