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

    Neuronpedia

    INDEX
    Explanations

    conditioner

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points (i.e. measurement values with fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jack
    -0.06
     Fred
    -0.06
    ARK
    -0.06
     bride
    -0.06
    可是
    -0.06
     Af
    -0.06
    овых
    -0.06
    _>
    -0.06
     camer
    -0.06
    owski
    -0.06
    POSITIVE LOGITS
    esktop
    0.06
     Jerome
    0.06
    (hero
    0.06
     Trails
    0.06
    με
    0.06
    anela
    0.06
     Geg
    0.06
    .nodeType
    0.06
    (Activity
    0.06
     +#+#+#+
    0.06
    Act Density 0.117%

    No Known Activations