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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects numeric score/confidence tokens — floating-point numbers (decimals) present in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    python
    -0.07
    承担
    -0.07
    סטודנט
    -0.06
    %%%%%%%%%%%%%%%%
    -0.06
    懵
    -0.06
    unch
    -0.06
    募集
    -0.06
    瑾
    -0.06
     nationals
    -0.06
     Broadcom
    -0.06
    POSITIVE LOGITS
    الجزائر
    0.08
    หลายคน
    0.08
    ählt
    0.07
    ퟰ
    0.07
    aldi
    0.07
    stellung
    0.06
    ategorized
    0.06
    �
    0.06
    .Concat
    0.06
    аль
    0.06
    Act Density 0.087%

    No Known Activations