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

    Neuronpedia

    INDEX
    Explanations

    academic studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compute
    -0.07
     interrupts
    -0.07
    highlight
    -0.07
    	size
    -0.07
     digits
    -0.07
     Highlights
    -0.07
     ions
    -0.07
    timeout
    -0.07
     keyof
    -0.07
    babel
    -0.06
    POSITIVE LOGITS
    .productId
    0.07
    ∘
    0.06
    _radio
    0.06
    |R
    0.06
     후
    0.06
    rik
    0.06
    ערכת
    0.06
    之作
    0.06
    OOT
    0.06
    ったら
    0.06
    Act Density 0.010%

    No Known Activations