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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ages
    -0.07
    ises
    -0.06
     belief
    -0.06
    aida
    -0.06
    kuk
    -0.06
     Hurt
    -0.06
    IMATE
    -0.06
    ousse
    -0.06
    Thomas
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
    SCREEN
    0.07
    (iParam
    0.07
    .LoadScene
    0.07
     вок
    0.07
    professional
    0.07
     GLint
    0.06
    (Api
    0.06
     QtCore
    0.06
    (AP
    0.06
    煙
    0.06
    Act Density 0.003%

    No Known Activations