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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    互联网
    -0.07
     onSubmit
    -0.06
    .ShouldBe
    -0.06
    HBoxLayout
    -0.06
    	W
    -0.06
     развитие
    -0.06
     Grandma
    -0.06
    /qu
    -0.06
    InParameter
    -0.06
    POSITIVE LOGITS
     addicts
    0.07
    atively
    0.07
     COR
    0.06
    -ps
    0.06
     payday
    0.06
    KK
    0.06
     moved
    0.06
    Ti
    0.06
    φαρ
    0.06
    _PREFIX
    0.06
    Act Density 0.008%

    No Known Activations