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

    Neuronpedia

    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens—especially floating-point numbers (tokens containing digits and a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ls
    -0.07
    λλά
    -0.07
    -deals
    -0.06
    ゅ
    -0.06
    Earlier
    -0.06
    чні
    -0.06
     شيء
    -0.06
    len
    -0.06
     conce
    -0.06
    ці
    -0.06
    POSITIVE LOGITS
     추
    0.06
    IMITER
    0.06
    .firestore
    0.06
    QRSTUV
    0.06
    <source
    0.06
     tabIndex
    0.06
    Information
    0.06
    _cent
    0.06
    .HE
    0.06
    BIT
    0.06
    Act Density 0.030%

    No Known Activations