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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on template “block” declarations (e.g. `{% block ... %}`) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     особи
    -0.07
    QN
    -0.07
     Wit
    -0.06
    νας
    -0.06
     Рос
    -0.06
    WA
    -0.06
     thru
    -0.06
     appoint
    -0.06
    しかし
    -0.06
    (the
    -0.06
    POSITIVE LOGITS
    VARCHAR
    0.07
     kredi
    0.07
     ::::::::
    0.06
     sala
    0.06
    毕
    0.06
     Traditional
    0.06
    _ST
    0.06
     nostalgic
    0.06
     Grammy
    0.06
                ↵
    0.06
    Act Density 0.001%

    No Known Activations