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

    Neuronpedia

    INDEX
    Explanations

    Referring to a figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rl
    -0.07
     hogy
    -0.06
    orderid
    -0.06
     быстро
    -0.06
     Helm
    -0.06
     �
    -0.06
    Town
    -0.06
    ับการ
    -0.06
     przed
    -0.06
    thumb
    -0.06
    POSITIVE LOGITS
     Fig
    0.08
    .socket
    0.07
    .").
    0.07
     Sexe
    0.06
     truyền
    0.06
     IsPlainOldData
    0.06
     presidents
    0.06
     injecting
    0.06
     '/')↵
    0.06
    stüt
    0.06
    Act Density 0.012%

    No Known Activations