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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     couple
    -0.07
     astonishing
    -0.06
     hissed
    -0.06
    ация
    -0.06
     disrupted
    -0.06
    (fp
    -0.06
     disagreement
    -0.06
    ации
    -0.06
     freezing
    -0.06
     раб
    -0.06
    POSITIVE LOGITS
     thắng
    0.07
     Ф
    0.07
     Drain
    0.07
     HH
    0.06
     DL
    0.06
     PLL
    0.06
    COMPLETE
    0.06
     SRC
    0.06
     Fish
    0.06
     podp
    0.06
    Act Density 0.000%

    No Known Activations