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

    Neuronpedia

    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Format
    -0.07
    .Import
    -0.07
     achievable
    -0.07
     близько
    -0.07
     wound
    -0.06
    Aspect
    -0.06
    Accuracy
    -0.06
    .include
    -0.06
    .Av
    -0.06
     Dx
    -0.06
    POSITIVE LOGITS
    cripts
    0.07
    stellar
    0.07
    .xlim
    0.06
     ├
    0.06
     relaciones
    0.06
     OW
    0.06
    cult
    0.06
    BuilderFactory
    0.06
    -shadow
    0.06
    فه
    0.06
    Act Density 0.035%

    No Known Activations