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

    Neuronpedia

    INDEX
    Explanations

    say "al word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anxiety
    -0.07
     notification
    -0.06
    ़ी
    -0.06
    	results
    -0.06
     تأثیر
    -0.06
     guardian
    -0.06
     creation
    -0.06
     lif
    -0.06
    内容
    -0.06
     table
    -0.06
    POSITIVE LOGITS
    odem
    0.07
    ValueCollection
    0.06
     minLength
    0.06
    arse
    0.06
    �
    0.06
    kok
    0.06
     مشک
    0.06
    �
    0.06
    ех
    0.06
    ampiyon
    0.06
    Act Density 0.005%

    No Known Activations