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

    Neuronpedia

    INDEX
    Explanations

    Counting numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     critic
    -0.07
    Directed
    -0.07
    nas
    -0.07
    -fix
    -0.06
    روط
    -0.06
     Christine
    -0.06
    993
    -0.06
     autofocus
    -0.06
     які
    -0.06
    하고
    -0.06
    POSITIVE LOGITS
    _velocity
    0.08
     Gn
    0.07
    /MPL
    0.06
    _meta
    0.06
    ']")↵
    0.06
     selecion
    0.06
    =name
    0.06
    ERVICE
    0.06
    riendly
    0.06
     千
    0.06
    Act Density 0.026%

    No Known Activations