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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    editar
    -0.07
    ь
    -0.07
     Martinez
    -0.06
    fifo
    -0.06
     Trades
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
     ITS
    -0.06
     plá
    -0.06
    _complete
    -0.06
     南
    -0.06
    POSITIVE LOGITS
    Friend
    0.06
     vera
    0.06
    わ
    0.06
    Leaks
    0.06
     enrollment
    0.06
     Bowl
    0.06
     confidential
    0.06
     elbows
    0.06
    ?)↵↵
    0.06
    Wel
    0.06
    Act Density 0.001%

    No Known Activations