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

    Neuronpedia

    INDEX
    Explanations

    repair services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Secret
    -0.07
    TT
    -0.07
    rd
    -0.06
    ouis
    -0.06
     idx
    -0.06
    ndo
    -0.06
    晶
    -0.06
    TOR
    -0.06
     smiled
    -0.06
    �nh
    -0.06
    POSITIVE LOGITS
    _exclude
    0.06
    _NAMESPACE
    0.06
    Recipe
    0.06
    _platform
    0.06
     Influence
    0.06
    ("
    0.06
     //*
    0.06
     zajímav
    0.06
    ूचन
    0.06
    urent
    0.06
    Act Density 0.129%

    No Known Activations