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

    Neuronpedia

    INDEX
    Explanations

    create

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    allback
    -0.08
     broad
    -0.08
    蒙
    -0.08
     encompass
    -0.07
     and
    -0.07
    发光
    -0.07
     pizza
    -0.07
    igma
    -0.07
     flags
    -0.07
     Wellness
    -0.07
    POSITIVE LOGITS
    معنى
    0.08
     ölçü
    0.07
    procedure
    0.07
    電子信箱
    0.07
    ⇋
    0.07
     can
    0.07
     constraints
    0.07
    מסר
    0.07
     mümkün
    0.07
    髓
    0.07
    Act Density 0.019%

    No Known Activations