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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harper
    -0.06
     vl
    -0.06
    λλά
    -0.06
     karş
    -0.06
     будто
    -0.06
     že
    -0.06
     Slug
    -0.06
    onestly
    -0.06
     út
    -0.06
    .cards
    -0.06
    POSITIVE LOGITS
    样的
    0.07
    :The
    0.07
     Unidos
    0.06
    [new
    0.06
     Showcase
    0.06
    %'↵
    0.06
    ριν
    0.06
    _Log
    0.06
     students
    0.06
    removed
    0.06
    Act Density 0.021%

    No Known Activations