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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orchestra
    -0.07
     QName
    -0.07
    乘
    -0.06
    \Module
    -0.06
     UIScreen
    -0.06
     Bru
    -0.06
     popup
    -0.06
     круг
    -0.06
    泡
    -0.06
    _masks
    -0.06
    POSITIVE LOGITS
     прош
    0.07
     profound
    0.07
     Однак
    0.07
     aest
    0.07
     можно
    0.06
    Install
    0.06
    readonly
    0.06
     Advisory
    0.06
    .local
    0.06
    DR
    0.06
    Act Density 0.231%

    No Known Activations