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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron detects definitional or descriptive “X is a Y”–style statements, activating on the copula “is” (often followed by “a”) that introduces a definition or description of the subject.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thrill
    -0.07
    fdb
    -0.06
    VRT
    -0.06
    ानव
    -0.06
    42
    -0.06
     Proc
    -0.06
     suspension
    -0.06
     fuck
    -0.06
     řid
    -0.06
     ensured
    -0.06
    POSITIVE LOGITS
    .
↵
    0.06
    .querySelectorAll
    0.06
    _bounds
    0.06
    �다
    0.06
    (=
    0.06
    Α
    0.06
     Donna
    0.06
    centage
    0.06
     scraps
    0.06
    dem
    0.06
    Act Density 0.055%

    No Known Activations