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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interest
    -0.07
    _enabled
    -0.07
     phiếu
    -0.07
     indem
    -0.07
    pose
    -0.06
    shutdown
    -0.06
    created
    -0.06
    SSION
    -0.06
    .listdir
    -0.06
     locom
    -0.06
    POSITIVE LOGITS
    �
    0.07
     보내
    0.06
    ]));↵↵
    0.06
    .TabControl
    0.06
    Dick
    0.06
     Auch
    0.06
     fkk
    0.06
     byteArray
    0.06
     أغ
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations