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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employees
    -0.06
     inherits
    -0.06
    _One
    -0.06
     Connectivity
    -0.06
    du
    -0.06
     Наз
    -0.06
    materials
    -0.06
    eper
    -0.06
     genocide
    -0.05
     の
    -0.05
    POSITIVE LOGITS
    .Photo
    0.07
     діє
    0.07
    	default
    0.07
    oppins
    0.07
     covert
    0.07
    .setCode
    0.06
     قي
    0.06
     Sachs
    0.06
    (point
    0.06
     scrimmage
    0.06
    Act Density 0.015%

    No Known Activations