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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fund
    -0.07
     highlighted
    -0.06
     مثال
    -0.06
    HS
    -0.06
    @
    -0.06
    PD
    -0.06
    OUTH
    -0.06
    rowsing
    -0.06
    IDAD
    -0.06
    CAC
    -0.06
    POSITIVE LOGITS
    ->[
    0.07
     Máy
    0.07
    (PDO
    0.06
    Multiplier
    0.06
     corr
    0.06
    Gene
    0.06
    ()?
    0.06
    horia
    0.06
     batching
    0.06
    	renderer
    0.06
    Act Density 0.001%

    No Known Activations