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

    Neuronpedia

    INDEX
    Explanations

    Code/documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bur
    -0.07
    ):\
    -0.06
    .monitor
    -0.06
    Encryption
    -0.06
     Dynamics
    -0.06
     Homes
    -0.06
     {}));↵
    -0.06
    ]=-
    -0.06
     Clair
    -0.06
    .connect
    -0.06
    POSITIVE LOGITS
    oss
    0.07
    acija
    0.07
    ublice
    0.07
    -wing
    0.06
     blasts
    0.06
    命周期
    0.06
    álně
    0.06
     فع
    0.06
    VICES
    0.06
    userName
    0.06
    Act Density 0.001%

    No Known Activations