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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric literals written as floating-point numbers (i.e., sequences containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stabil
    -0.07
     Hardcore
    -0.06
    Beth
    -0.06
    .barDockControl
    -0.06
    canvas
    -0.06
    apsible
    -0.06
    (metadata
    -0.06
    _requires
    -0.06
    �
    -0.06
    ActivityIndicatorView
    -0.06
    POSITIVE LOGITS
    _sum
    0.08
     позитив
    0.07
     sum
    0.07
     votes
    0.07
    Sum
    0.07
    .AddField
    0.06
    CEO
    0.06
     hdf
    0.06
    _colour
    0.06
    _rg
    0.06
    Act Density 0.045%

    No Known Activations