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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    에
    -0.07
     promoter
    -0.06
    llx
    -0.06
    ｗｗ
    -0.06
    �
    -0.06
    ünkü
    -0.06
     collision
    -0.06
    multiple
    -0.06
    ste
    -0.06
     TVs
    -0.06
    POSITIVE LOGITS
     Experienced
    0.07
     문
    0.07
     Ster
    0.06
     maintaining
    0.06
     должно
    0.06
     Provided
    0.06
    _vlan
    0.06
     Mines
    0.06
    _connections
    0.06
     Salv
    0.06
    Act Density 0.276%

    No Known Activations