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

    Neuronpedia

    INDEX
    Explanations

    ib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Victims
    -0.07
     zlat
    -0.07
    敏
    -0.07
    oston
    -0.06
    orda
    -0.06
     victims
    -0.06
    遍
    -0.06
     menace
    -0.06
    リスト
    -0.06
    шими
    -0.06
    POSITIVE LOGITS
    /j
    0.07
    Properties
    0.06
     必
    0.06
    hf
    0.06
    uploaded
    0.06
     incarn
    0.06
     nj
    0.06
     minib
    0.06
    ाय
    0.06
    raig
    0.06
    Act Density 0.000%

    No Known Activations