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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compan
    -0.07
     Kam
    -0.07
     нових
    -0.07
     collaps
    -0.07
     multim
    -0.06
     हमल
    -0.06
     आख
    -0.06
    Το
    -0.06
     Hamilton
    -0.06
     Rep
    -0.06
    POSITIVE LOGITS
    骑
    0.06
    сон
    0.06
    normalize
    0.06
     logos
    0.06
    ographical
    0.06
    -short
    0.06
    ệ
    0.06
      ↵↵
    0.06
    _LABEL
    0.06
     reputed
    0.06
    Act Density 0.000%

    No Known Activations