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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .controllers
    -0.08
     clever
    -0.07
    .MM
    -0.07
    arding
    -0.07
    -pound
    -0.07
     indiscrim
    -0.07
     Moreno
    -0.07
     Rio
    -0.07
     experimentation
    -0.07
     Cho
    -0.07
    POSITIVE LOGITS
    ᾔ
    0.07
    [:]
    0.07
     réal
    0.07
     문제가
    0.07
     cognitive
    0.07
     userList
    0.06
    精神
    0.06
    عب
    0.06
    asString
    0.06
     onPage
    0.06
    Act Density 0.063%

    No Known Activations