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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    secured
    -0.07
    Dirs
    -0.06
    مه
    -0.06
    Authentication
    -0.06
    angling
    -0.06
     vice
    -0.06
    encryption
    -0.06
     userInfo
    -0.06
    another
    -0.06
    랑스
    -0.06
    POSITIVE LOGITS
     only
    0.07
    /th
    0.07
     short
    0.07
     FL
    0.06
    (hwnd
    0.06
     jlong
    0.06
     ◆
    0.06
    Hol
    0.06
     ask
    0.06
     таком
    0.06
    Act Density 0.025%

    No Known Activations