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

    Neuronpedia

    INDEX
    Explanations

    professionals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studios
    -0.07
    ред
    -0.06
     plants
    -0.06
    yard
    -0.06
     dateString
    -0.06
    学生
    -0.06
     forecasting
    -0.06
    _management
    -0.06
    manager
    -0.06
    στημα
    -0.06
    POSITIVE LOGITS
     devs
    0.07
    sgi
    0.06
    Indices
    0.06
    _IMAGE
    0.06
    .Design
    0.06
    ,char
    0.06
    PLIC
    0.06
     필
    0.06
    lsru
    0.06
     Savaşı
    0.06
    Act Density 0.048%

    No Known Activations