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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tutorials
    -0.06
     dripping
    -0.06
    modern
    -0.06
    tea
    -0.06
    deposit
    -0.06
    Arrange
    -0.06
    idence
    -0.06
    _expression
    -0.06
    _AdjustorThunk
    -0.06
    awk
    -0.06
    POSITIVE LOGITS
    icho
    0.07
    ,G
    0.07
     _______,
    0.06
     güvenlik
    0.06
     pasar
    0.06
     كر
    0.06
    .tel
    0.06
     stranded
    0.06
    ,node
    0.06
    範
    0.06
    Act Density 0.025%

    No Known Activations