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

    Neuronpedia

    INDEX
    Explanations

    Logic and probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welcomes
    -0.08
    _tag
    -0.07
    Aut
    -0.07
     А
    -0.07
    .Le
    -0.06
    -Le
    -0.06
     Psy
    -0.06
    еться
    -0.06
     cerc
    -0.06
     AC
    -0.06
    POSITIVE LOGITS
    >'
↵
    0.07
     mListener
    0.06
    }>{
    0.06
     金
    0.06
     VK
    0.06
     kodu
    0.06
    '=>"
    0.06
     Han
    0.06
    .runner
    0.06
     getActivity
    0.06
    Act Density 0.008%

    No Known Activations