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

    Neuronpedia

    INDEX
    Explanations

    heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ています
    -0.07
     именно
    -0.06
    ãy
    -0.06
     саме
    -0.06
    ỷ
    -0.06
    (vm
    -0.06
     объем
    -0.06
    	td
    -0.06
    .bpm
    -0.06
    柱
    -0.06
    POSITIVE LOGITS
     Die
    0.08
    Ownership
    0.07
    -popup
    0.07
    -aut
    0.07
    avior
    0.07
    aida
    0.07
     shutter
    0.06
    _MR
    0.06
     Mont
    0.06
     ERA
    0.06
    Act Density 0.196%

    No Known Activations