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

    Neuronpedia

    INDEX
    Explanations

    -n

    np_max-act · gemini-2.0-flash

    The neuron flags sentence‐boundary cues and proper‐name tokens—i.e. punctuation at the end of sentences and the capitalized words that start sentences or form named entities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .DataBindings
    -0.07
     Diet
    -0.07
    .loaded
    -0.06
    (pc
    -0.06
    /save
    -0.06
     предполаг
    -0.06
     antibiotics
    -0.06
     Beautiful
    -0.06
    backward
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
     �
    0.06
    0.06
     ordin
    0.06
     малень
    0.06
    thalm
    0.06
     메
    0.06
     세
    0.06
     utiliser
    0.06
    ்
    0.06
     جي
    0.06
    Act Density 0.137%

    No Known Activations