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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron fires on “as…or as…” comparative constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yüz
    -0.07
    _play
    -0.07
     estimation
    -0.06
    ……↵↵
    -0.06
    THON
    -0.06
    Parent
    -0.06
    ělí
    -0.06
    _RX
    -0.06
     دع
    -0.06
     rpc
    -0.06
    POSITIVE LOGITS
     Conservative
    0.07
    (P
    0.06
     Toshiba
    0.06
     ポ
    0.06
    OGRAPH
    0.06
    GCC
    0.06
     heir
    0.06
     mayor
    0.06
     Putin
    0.06
     сор
    0.06
    Act Density 0.076%

    No Known Activations