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

    Neuronpedia

    INDEX
    Explanations

    pliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     déc
    -0.07
    "There
    -0.07
    	Vector
    -0.07
    ิทยาศาสตร
    -0.06
    “There
    -0.06
    XObject
    -0.06
    อต
    -0.06
    ero
    -0.06
    ift
    -0.06
     Era
    -0.06
    POSITIVE LOGITS
     compliance
    0.10
     Compliance
    0.09
    pliance
    0.08
     complying
    0.07
     compliant
    0.07
     CPL
    0.07
    formance
    0.07
    Exclude
    0.07
    ši
    0.06
    藥
    0.06
    Act Density 0.011%

    No Known Activations