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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的品牌
    -0.08
    ことです
    -0.07
     labeling
    -0.07
     categoryName
    -0.07
    Their
    -0.07
    klär
    -0.07
     наши
    -0.07
    мен
    -0.07
    _visit
    -0.07
     паци
    -0.07
    POSITIVE LOGITS
    -io
    0.07
    历程
    0.07
    ⵉ
    0.07
     system
    0.06
    mf
    0.06
    0.06
     لهذا
    0.06
    	UFUNCTION
    0.06
    Solver
    0.06
    _r
    0.06
    Act Density 0.000%

    No Known Activations