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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric literals with decimal points (floating-point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pupil
    -0.07
     hb
    -0.07
    .root
    -0.06
     })(
    -0.06
     Dropout
    -0.06
     tk
    -0.06
    (choices
    -0.06
     Fork
    -0.06
     Wort
    -0.06
     }}</
    -0.06
    POSITIVE LOGITS
    ometric
    0.07
    áy
    0.07
    airport
    0.07
    _authentication
    0.06
    @GetMapping
    0.06
     unthinkable
    0.06
     Transmit
    0.06
    َج
    0.06
    -Dec
    0.06
     commercially
    0.06
    Act Density 0.101%

    No Known Activations