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

    Neuronpedia

    INDEX
    Explanations

    Providing resources and support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    restrial
    -0.06
    ờ
    -0.06
    σταν
    -0.06
    room
    -0.06
     classification
    -0.06
     Dana
    -0.06
    ylation
    -0.06
     door
    -0.06
     markets
    -0.06
    Rooms
    -0.06
    POSITIVE LOGITS
    AVAILABLE
    0.07
     init
    0.06
    "..
    0.06
     면
    0.06
    :)])
    0.06
    かって
    0.06
    placeholder
    0.06
    .single
    0.06
     allen
    0.06
    /log
    0.06
    Act Density 0.085%

    No Known Activations