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

    Neuronpedia

    INDEX
    Explanations

    latter

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on the word “latter,” i.e. instances of “latter” used to refer back to a preceding item.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _manage
    -0.08
     GP
    -0.07
    .Do
    -0.07
     analyzes
    -0.07
    ูนย
    -0.07
    tgl
    -0.07
    UGE
    -0.07
     Ana
    -0.07
    bags
    -0.07
     لیگ
    -0.07
    POSITIVE LOGITS
     latter
    0.13
    atter
    0.07
     بوده
    0.07
     typo
    0.07
    Τ
    0.07
     Reaper
    0.07
    der
    0.06
     Latter
    0.06
     GLUT
    0.06
     згод
    0.06
    Act Density 0.006%

    No Known Activations