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

    Neuronpedia

    INDEX
    Explanations

    beginning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ben
    -0.07
    _LINE
    -0.07
    Ben
    -0.06
    idenav
    -0.06
    (fname
    -0.06
     gl
    -0.06
    �新
    -0.06
    омер
    -0.06
    bear
    -0.06
     adipiscing
    -0.06
    POSITIVE LOGITS
     beginning
    0.10
    Toe
    0.07
     poč
    0.07
    得
    0.07
     induce
    0.06
    ItemClickListener
    0.06
    ，因为
    0.06
    €↵
    0.06
     деле
    0.06
    err
    0.06
    Act Density 0.085%

    No Known Activations