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

    Neuronpedia

    INDEX
    Explanations

    Security vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancell
    -0.07
    ễn
    -0.07
    茝
    -0.07
    ╮
    -0.07
     właś
    -0.07
    笮
    -0.07
    ்
    -0.07
    firstname
    -0.06
    ه
    -0.06
    Illegal
    -0.06
    POSITIVE LOGITS
    errals
    0.07
    cence
    0.07
     élèves
    0.06
    riere
    0.06
    карт
    0.06
    antity
    0.06
     nurturing
    0.06
     Dy
    0.06
    子里
    0.06
    (extra
    0.06
    Act Density 0.020%

    No Known Activations