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

    Neuronpedia

    INDEX
    Explanations

    causality and possibility

    np_max-act · gemini-2.0-flash

    This neuron activates on phrasing that describes available options or choices (e.g. “choice … have … in terms of”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Araştır
    -0.07
    _tuples
    -0.06
    interop
    -0.06
    .XtraReports
    -0.06
    Cart
    -0.06
    mscorlib
    -0.06
    INCLUDE
    -0.06
     iov
    -0.06
     já
    -0.06
    Assignable
    -0.06
    POSITIVE LOGITS
    ondere
    0.07
     baseline
    0.06
    CAA
    0.06
    καν
    0.06
    руг
    0.06
    Pixels
    0.06
     technician
    0.06
    的大
    0.06
     imaginary
    0.06
    _ENT
    0.06
    Act Density 0.103%

    No Known Activations