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

    Neuronpedia

    INDEX
    Explanations

    Walking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ️
    -0.07
     zaměst
    -0.07
     ici
    -0.06
    とした
    -0.06
    jb
    -0.06
    resume
    -0.06
     valores
    -0.06
    -second
    -0.06
    ⠀
    -0.06
    -no
    -0.06
    POSITIVE LOGITS
     teg
    0.08
    -orange
    0.07
     Exercises
    0.07
    _Process
    0.07
     strokeLine
    0.07
    ,opt
    0.07
    (age
    0.06
    Ocean
    0.06
    (let
    0.06
    (ext
    0.06
    Act Density 0.007%

    No Known Activations