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

    Neuronpedia

    INDEX
    Explanations

    Welcome, problem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -assets
    -0.07
     Ayrıca
    -0.07
    lerde
    -0.07
    y
    -0.06
    ())
↵
↵
    -0.06
    .Statement
    -0.06
     miejsc
    -0.06
     dinheiro
    -0.06
    svg
    -0.06
     şik
    -0.06
    POSITIVE LOGITS
     bibli
    0.07
     blends
    0.06
     unthinkable
    0.06
    ible
    0.06
     Wonderland
    0.06
    途
    0.06
     Purpose
    0.06
     alright
    0.06
     whirl
    0.06
     µ
    0.06
    Act Density 0.007%

    No Known Activations