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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tra
    -0.07
    После
    -0.07
    盒
    -0.07
    .sessions
    -0.06
    .getX
    -0.06
    _middle
    -0.06
     сентября
    -0.06
     ideals
    -0.06
    _HANDLE
    -0.06
     Prague
    -0.06
    POSITIVE LOGITS
     Вас
    0.07
    /"
    0.07
    icial
    0.07
    огра
    0.07
    _OF
    0.07
    ATIC
    0.07
     ss
    0.06
    Decode
    0.06
    URLConnection
    0.06
    urf
    0.06
    Act Density 0.016%

    No Known Activations