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

    Neuronpedia

    INDEX
    Explanations

    Human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ufs
    -0.07
    lux
    -0.06
    357
    -0.06
    many
    -0.06
    commended
    -0.06
     default
    -0.06
    uf
    -0.06
    -0.06
    -resistant
    -0.06
    clients
    -0.06
    POSITIVE LOGITS
     appear
    0.07
    È
    0.07
    TITLE
    0.06
     тепер
    0.06
    ังคม
    0.06
     concentrating
    0.06
     trabalho
    0.06
    notated
    0.06
    _TCP
    0.06
    ách
    0.06
    Act Density 0.025%

    No Known Activations