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

    Neuronpedia

    INDEX
    Explanations

    Australia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expressly
    -0.07
     stern
    -0.07
     exists
    -0.07
     reader
    -0.07
    Kay
    -0.06
     startling
    -0.06
     occupational
    -0.06
     tension
    -0.06
    algorithm
    -0.06
     questioned
    -0.06
    POSITIVE LOGITS
    +"\
    0.08
    +".
    0.07
    ımıza
    0.06
    nton
    0.06
    طي
    0.06
     Mavericks
    0.06
    acion
    0.06
    �
    0.06
    _hz
    0.06
    uzzer
    0.06
    Act Density 0.031%

    No Known Activations