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

    Neuronpedia

    INDEX
    Explanations

    profession

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on the word “profession” (and its plural “professions”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     total
    -0.07
     joy
    -0.07
     sake
    -0.07
    Loop
    -0.07
     tantal
    -0.07
     nug
    -0.07
     oil
    -0.07
     Carlos
    -0.06
     smaller
    -0.06
     Yar
    -0.06
    POSITIVE LOGITS
     profession
    0.12
     professions
    0.10
     предназнач
    0.08
     Profession
    0.07
    .sendFile
    0.07
     професси
    0.07
    .tagName
    0.07
     абсолютно
    0.07
    ㅠ
    0.07
    .charAt
    0.07
    Act Density 0.012%

    No Known Activations