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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expenses
    -0.09
    expenses
    -0.09
    Expenses
    -0.09
     mily
    -0.08
    dtype
    -0.08
    成本
    -0.08
     Expenses
    -0.08
    NSInteger
    -0.08
    ERROR
    -0.08
    displaystyle
    -0.08
    POSITIVE LOGITS
     Represent
    0.08
     המד
    0.08
     répart
    0.08
     Эти
    0.07
     sabor
    0.07
     יכולים
    0.07
     représentant
    0.07
     Spatial
    0.07
     fict
    0.07
     gezamen
    0.07
    Act Density 0.217%

    No Known Activations