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

    Neuronpedia

    INDEX
    Explanations

    men

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens containing the letter sequence “men” (e.g. in names like Menal, Menhaden, Menken).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Arctic
    -0.07
    úc
    -0.07
    arc
    -0.07
    icro
    -0.07
    ARC
    -0.07
     Turbo
    -0.07
    Circular
    -0.07
    604
    -0.07
    RFC
    -0.07
    禮
    -0.06
    POSITIVE LOGITS
    Man
    0.09
     don
    0.09
    /man
    0.09
    Mom
    0.09
    man
    0.08
     mn
    0.08
     Son
    0.08
     Man
    0.07
    .number
    0.07
    .Man
    0.07
    Act Density 0.020%

    No Known Activations