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

    Neuronpedia

    INDEX
    Explanations

    knit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hitters
    -0.07
    езда
    -0.07
    endance
    -0.07
    �
    -0.06
     Josh
    -0.06
     plane
    -0.06
     superstar
    -0.06
    apesh
    -0.06
    يف
    -0.06
    -mask
    -0.06
    POSITIVE LOGITS
     Minecraft
    0.06
    	else
    0.06
    German
    0.06
     krát
    0.06
     tasty
    0.06
    TEX
    0.06
     ∀
    0.06
     luckily
    0.06
    _between
    0.06
    [{
    0.06
    Act Density 0.012%

    No Known Activations