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

    Neuronpedia

    INDEX
    Explanations

    Third

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the numeral “3” when it appears in legal‐citation strings (e.g. in “3d” to denote the Third District or volume).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    subclass
    -0.07
    _polygon
    -0.06
    .dart
    -0.06
    iu
    -0.06
     erroneous
    -0.06
     coloc
    -0.06
    wm
    -0.06
    nonatomic
    -0.06
    .with
    -0.06
     implement
    -0.06
    POSITIVE LOGITS
     TRY
    0.07
    undefined
    0.06
    acr
    0.06
     Drinks
    0.06
     ş
    0.06
     �
    0.06
     outro
    0.06
     haar
    0.06
    -value
    0.06
    십
    0.06
    Act Density 0.004%

    No Known Activations