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

    Neuronpedia

    INDEX
    Explanations

    actions of creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sculpted
    -1.27
    rungsseite
    -1.18
     carved
    -1.10
    الحياه
    -1.09
     brewed
    -1.09
     متعلقه
    -1.08
     moulded
    -1.08
     виправивши
    -1.08
    ergies
    -1.03
     shaped
    -1.02
    POSITIVE LOGITS
     out
    0.81
     
    0.68
     most
    0.64
     into
    0.64
    出
    0.59
     up
    0.56
     over
    0.56
     using
    0.55
     initial
    0.54
     the
    0.52
    Act Density 0.026%

    No Known Activations