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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act · gemini-2.0-flash

    The neuron specifically detects numeric tokens within personal identifying number sequences (e.g., phone‐number digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     İngilizce
    -0.07
    FPS
    -0.07
     '\"
    -0.06
    wner
    -0.06
    Sharp
    -0.06
    <<<<
    -0.06
     -----↵
    -0.06
     yüksek
    -0.06
     Coul
    -0.06
     Đề
    -0.06
    POSITIVE LOGITS
     dang
    0.06
     навіть
    0.06
     степ
    0.06
    باشد
    0.06
     которой
    0.06
    OBJ
    0.06
     Sgt
    0.05
     MPs
    0.05
     Pretty
    0.05
     Mediterr
    0.05
    Act Density 0.014%

    No Known Activations