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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    крас
    -0.07
    漂亮
    -0.06
     identification
    -0.06
    iscrim
    -0.06
    NESS
    -0.06
     antid
    -0.06
     Deutschland
    -0.06
     bán
    -0.06
    fk
    -0.06
    zd
    -0.06
    POSITIVE LOGITS
     Automated
    0.08
    .rooms
    0.08
     bowed
    0.07
    tablet
    0.07
     Investigations
    0.07
    实现了
    0.07
     初始化
    0.07
    Tuple
    0.07
     retract
    0.07
    dbo
    0.07
    Act Density 0.001%

    No Known Activations