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

    Neuronpedia

    INDEX
    Explanations

    keys

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of “key” (and its plural form) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _clause
    -0.07
    _Number
    -0.06
    stial
    -0.06
    oufl
    -0.06
    ふ
    -0.06
    ์)
    -0.06
    HorizontalAlignment
    -0.06
     Ips
    -0.06
    庄
    -0.06
     首页
    -0.06
    POSITIVE LOGITS
     Респ
    0.07
     cheesy
    0.07
     poorer
    0.07
     py
    0.06
     staircase
    0.06
     noteworthy
    0.06
     courtyard
    0.06
     platinum
    0.06
    tahun
    0.06
     verdi
    0.06
    Act Density 0.005%

    No Known Activations