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

    Neuronpedia

    INDEX
    Explanations

    studies with children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     никогда
    -0.08
     câ
    -0.07
    _CLASS
    -0.07
    以上的
    -0.07
    .CONNECT
    -0.06
     accusing
    -0.06
    similar
    -0.06
    (rename
    -0.06
    cfg
    -0.06
     Never
    -0.06
    POSITIVE LOGITS
    美味
    0.07
    yyy
    0.07
    퀸
    0.07
    重庆市
    0.07
     ~/.
    0.07
     Maison
    0.06
    ONGL
    0.06
    ありが
    0.06
     needing
    0.06
    wares
    0.06
    Act Density 0.049%

    No Known Activations