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

    Neuronpedia

    INDEX
    Explanations

    gerunds and quotations

    np_max-act · gemini-2.0-flash

    The neuron responds to words in their “-ing” form—that is, gerund or present-participle verbs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fortn
    -0.07
     clos
    -0.07
     ",",
    -0.06
    ermann
    -0.06
    驚
    -0.06
     initializes
    -0.06
    πισ
    -0.06
     Relationships
    -0.06
    _ROM
    -0.06
    SELF
    -0.06
    POSITIVE LOGITS
    Ü
    0.07
    _ARCHIVE
    0.07
     �
    0.07
    TAB
    0.06
     شیمی
    0.06
     felse
    0.06
     birlik
    0.06
     الخط
    0.06
    祖
    0.06
     आर
    0.06
    Act Density 0.169%

    No Known Activations