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

    Neuronpedia

    INDEX
    Explanations

    surname

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cu
    -0.08
     recruiter
    -0.07
     chiefs
    -0.07
     probation
    -0.07
     userManager
    -0.07
    .onViewCreated
    -0.07
     DTO
    -0.07
     Chiefs
    -0.07
    “A
    -0.06
     chu
    -0.06
    POSITIVE LOGITS
     surname
    0.07
    ![↵
    0.06
    av
    0.06
    .':
    0.06
    meta
    0.06
    :white
    0.06
    :first
    0.06
    SetColor
    0.06
    unexpected
    0.06
    =np
    0.06
    Act Density 0.003%

    No Known Activations