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

    Neuronpedia

    INDEX
    Explanations

    Blender

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accomp
    -0.07
    父母
    -0.07
     laughs
    -0.07
    Documentation
    -0.07
    ASK
    -0.07
    .Tasks
    -0.07
    顾客
    -0.07
    _FAIL
    -0.06
     Uint
    -0.06
     infectious
    -0.06
    POSITIVE LOGITS
     blender
    0.07
     liner
    0.07
    嵘
    0.07
    _
↵
    0.07
     Blender
    0.07
     intl
    0.07
     중국
    0.07
    _,↵
    0.07
    หร
    0.07
     thế
    0.07
    Act Density 0.001%

    No Known Activations