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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron activates on sequences of digits (e.g. phone‐number fragments or other numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    66
    -0.07
    voor
    -0.07
    06
    -0.07
    ibraries
    -0.07
    .There
    -0.07
     dias
    -0.07
     कड
    -0.07
    ाठ
    -0.07
    49
    -0.06
    55
    -0.06
    POSITIVE LOGITS
    ());
↵
    0.07
    بی
    0.06
     yelled
    0.06
     Cosmic
    0.06
     ارزش
    0.06
    saved
    0.06
     позвол
    0.06
    Mrs
    0.06
    ยาน
    0.06
     pinterest
    0.06
    Act Density 0.008%

    No Known Activations