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

    Neuronpedia

    INDEX
    Explanations

    Dates in medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adversity
    -0.08
     Privacy
    -0.07
    itizen
    -0.07
     comfort
    -0.07
    combat
    -0.06
    _REPLACE
    -0.06
     retirement
    -0.06
    formulario
    -0.06
    ㉨
    -0.06
    𝚆
    -0.06
    POSITIVE LOGITS
    )}↵
    0.07
     los
    0.07
     gái
    0.07
    -s
    0.06
    mys
    0.06
     pos
    0.06
    pr
    0.06
    —is
    0.06
    mapping
    0.06
    —including
    0.06
    Act Density 0.022%

    No Known Activations