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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of studies or data in humans, i.e. occurrences of the word "humans" (often with a numerical value).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ственного
    -0.06
    Btn
    -0.06
    rette
    -0.06
     Assistance
    -0.06
    Ing
    -0.06
    jištění
    -0.06
     Playback
    -0.06
     Vic
    -0.06
    022
    -0.06
     आश
    -0.06
    POSITIVE LOGITS
     searchBar
    0.07
    {$
    0.07
     �
    0.06
    posing
    0.06
     germany
    0.06
     cùng
    0.06
    />↵
    0.06
    .Has
    0.06
     لكل
    0.06
    making
    0.06
    Act Density 0.011%

    No Known Activations