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

    Neuronpedia

    INDEX
    Explanations

    Presentation transcripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    微
    -0.07
    _pins
    -0.07
     ситуации
    -0.07
    (js
    -0.06
    anela
    -0.06
    Gate
    -0.06
    falls
    -0.06
    Towards
    -0.06
    _qs
    -0.06
    >"
↵
    -0.06
    POSITIVE LOGITS
     wish
    0.06
    (Graphics
    0.06
     alcoholic
    0.06
    県
    0.06
     can
    0.06
     Walsh
    0.06
     immortal
    0.06
     ภาษ
    0.06
     Lt
    0.06
    网
    0.06
    Act Density 0.024%

    No Known Activations