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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -debug
    -0.07
    .Startup
    -0.07
    /bash
    -0.07
     inclination
    -0.07
     propio
    -0.07
    mí
    -0.06
     sollen
    -0.06
     lifting
    -0.06
    Installation
    -0.06
    level
    -0.06
    POSITIVE LOGITS
     informací
    0.07
    .Val
    0.06
     eas
    0.06
    €�
    0.06
    .IsNotNull
    0.06
     overs
    0.06
     Mohamed
    0.06
     �
    0.06
    िसम
    0.06
    `)
    0.06
    Act Density 0.003%

    No Known Activations