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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (decimal values) in CSS declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     сосуд
    -0.08
    Knight
    -0.07
    iná
    -0.07
    "For
    -0.07
    .↵↵↵↵↵↵↵↵
    -0.07
     ";↵↵
    -0.07
     fragile
    -0.07
     mnist
    -0.07
     Editors
    -0.06
    ()↵↵↵
    -0.06
    POSITIVE LOGITS
    하였다
    0.08
    ?}",
    0.06
    acl
    0.06
    itto
    0.06
    verted
    0.06
    ागत
    0.06
    nev
    0.06
     apk
    0.06
    _Impl
    0.05
    �
    0.05
    Act Density 0.002%

    No Known Activations