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

    Neuronpedia

    INDEX
    Explanations

    planets transiting

    np_max-act · gemini-2.0-flash

    The neuron activates on subword fragments of “transit” (e.g. “trans‐” + “iting”) and thus detects mentions of planetary transits.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "A
    -0.07
     Marian
    -0.06
     gastr
    -0.06
     Cr
    -0.06
     본
    -0.06
    otte
    -0.06
    ,
↵
    -0.06
    xmm
    -0.06
    .MixedReality
    -0.06
     Bare
    -0.06
    POSITIVE LOGITS
     Firefox
    0.06
    лина
    0.06
    และส
    0.06
    -faced
    0.06
    Netflix
    0.06
    Equip
    0.06
    rama
    0.06
    Н
    0.06
    -ie
    0.06
     recognized
    0.06
    Act Density 0.001%

    No Known Activations