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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_max-act · gemini-2.0-flash

    This neuron activates on dotted array-method calls (e.g. `.map`, `.filter`, `.concat`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    antwort
    -0.07
     receiver
    -0.06
     Reports
    -0.06
     blocker
    -0.06
    lém
    -0.06
     soutěže
    -0.06
    (round
    -0.06
    cycl
    -0.06
     здоров
    -0.06
     worn
    -0.06
    POSITIVE LOGITS
     Towers
    0.07
    .optional
    0.06
    ("***
    0.06
     tubes
    0.06
    後に
    0.06
     ['
    0.06
    .draw
    0.06
    Short
    0.06
    .ViewModel
    0.06
     어떤
    0.06
    Act Density 0.012%

    No Known Activations