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

    Neuronpedia

    INDEX
    Explanations

    Software dependencies and configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ngthen
    -0.07
    这是我
    -0.07
    arding
    -0.07
    蚕
    -0.06
     Linda
    -0.06
    搓
    -0.06
    ании
    -0.06
    beros
    -0.06
    ighth
    -0.06
    cri
    -0.06
    POSITIVE LOGITS
    -social
    0.10
     Structural
    0.08
     biases
    0.08
    =search
    0.07
     Scientists
    0.07
     الإير
    0.07
    类型
    0.07
     Panels
    0.07
     Charges
    0.07
    :Int
    0.07
    Act Density 0.004%

    No Known Activations