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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implanted
    -0.07
     empowering
    -0.06
     grandfather
    -0.06
     holy
    -0.06
    _Player
    -0.06
     insulting
    -0.06
    _MESH
    -0.06
    增加
    -0.06
    _ips
    -0.06
    价值
    -0.06
    POSITIVE LOGITS
    Ğİ
    0.07
     embodied
    0.07
    ilon
    0.06
    ?]
    0.06
    veillance
    0.06
    .CommandType
    0.06
    ura
    0.06
    ).'
    0.06
    .gamma
    0.06
    etest
    0.06
    Act Density 0.000%

    No Known Activations