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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ераль
    -0.07
     ของ
    -0.07
     eos
    -0.07
    ठन
    -0.06
    _tuple
    -0.06
     khối
    -0.06
     della
    -0.06
    إ
    -0.06
     первую
    -0.06
    oultry
    -0.06
    POSITIVE LOGITS
     These
    0.08
     are
    0.07
       
    0.07
     Clim
    0.07
     as
    0.07
     My
    0.06
     envoy
    0.06
    —we
    0.06
    sim
    0.06
    ?,?,
    0.06
    Act Density 0.155%

    No Known Activations