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

    Neuronpedia

    INDEX
    Explanations

    ив

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Somerset
    -0.08
     excursion
    -0.08
     interactions
    -0.07
    иров
    -0.07
     инт
    -0.07
    qubo
    -0.07
    appy
    -0.07
    Interactions
    -0.07
    �
    -0.07
     взаимодейств
    -0.07
    POSITIVE LOGITS
     venc
    0.09
     teeth
    0.09
    atoren
    0.08
     disposed
    0.08
     filtration
    0.08
    totypes
    0.08
    bros
    0.08
    -water
    0.08
    foto
    0.08
     disposal
    0.08
    Act Density 0.007%

    No Known Activations