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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roles
    -0.07
     posts
    -0.06
     Starts
    -0.06
     hudeb
    -0.06
    -qu
    -0.06
     mont
    -0.06
    ivities
    -0.06
     Reform
    -0.06
     voices
    -0.06
    аф
    -0.06
    POSITIVE LOGITS
     तरह
    0.06
    [self
    0.06
    下去
    0.06
    _published
    0.06
     مهندسی
    0.06
    
    0.06
    .Tipo
    0.06
    GetProperty
    0.06
     presenta
    0.06
     İyi
    0.06
    Act Density 0.022%

    No Known Activations