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

    Neuronpedia

    INDEX
    Explanations

    sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilty
    -0.07
     attacked
    -0.07
    _number
    -0.06
    -fold
    -0.06
    Gap
    -0.06
    udev
    -0.06
    _BP
    -0.06
     Du
    -0.06
     Identity
    -0.06
     coincidence
    -0.06
    POSITIVE LOGITS
    �
    0.07
     tục
    0.06
     malaysia
    0.06
    /left
    0.06
    avatel
    0.06
    орм
    0.06
     tela
    0.06
     타
    0.06
    Basket
    0.06
    agento
    0.06
    Act Density 0.007%

    No Known Activations