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

    Neuronpedia

    INDEX
    Explanations

    hug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >

↵
    -0.07
    	de
    -0.07
     شامل
    -0.07
    空间
    -0.06
     месяцев
    -0.06
    Root
    -0.06
     уча
    -0.06
     conv
    -0.06
    zeigt
    -0.06
     proyecto
    -0.06
    POSITIVE LOGITS
     tern
    0.07
    511
    0.06
     Tub
    0.06
    .Utilities
    0.06
    ージ
    0.06
    Rep
    0.06
    �
    0.06
    .Require
    0.06
    収
    0.06
     Planet
    0.05
    Act Density 0.000%

    No Known Activations