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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vault
    -0.08
     Confeder
    -0.06
    	unsigned
    -0.06
    нож
    -0.06
    controller
    -0.06
    control
    -0.06
    vp
    -0.06
    (repo
    -0.06
    Geometry
    -0.06
    fluence
    -0.06
    POSITIVE LOGITS
     dní
    0.07
    .`|`↵
    0.07
     institution
    0.06
    Scalars
    0.06
     out
    0.06
    (code
    0.06
    .writerow
    0.06
     ='
    0.06
    !I
    0.06
     pleasure
    0.06
    Act Density 0.053%

    No Known Activations