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

    Neuronpedia

    INDEX
    Explanations

    Code/ML snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     запрос
    -0.08
     cable
    -0.08
     matric
    -0.08
     еж
    -0.08
     tongue
    -0.08
    {|
    -0.07
     computations
    -0.07
    Graf
    -0.07
    ಚಿತ್ರ
    -0.07
    Мне
    -0.07
    POSITIVE LOGITS
     fitter
    0.09
     Gwyn
    0.09
     Runner
    0.08
     Insp
    0.08
     Agent
    0.08
     Sergio
    0.08
     Equal
    0.08
    Consts
    0.08
     Ita
    0.08
     Fernández
    0.08
    Act Density 0.001%

    No Known Activations