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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     หม
    -0.07
    mdb
    -0.07
    queen
    -0.07
     мор
    -0.06
    给
    -0.06
    .proj
    -0.06
     gastr
    -0.06
    통
    -0.06
     Lud
    -0.06
     민주
    -0.06
    POSITIVE LOGITS
    .setCode
    0.07
     contributions
    0.06
    ennial
    0.06
    .newaxis
    0.06
    .Escape
    0.06
    inclu
    0.06
    ittest
    0.06
     Hedge
    0.06
    -script
    0.06
    _grade
    0.06
    Act Density 0.022%

    No Known Activations