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

    Neuronpedia

    INDEX
    Explanations

    slide numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Release
    -0.07
     jb
    -0.06
    (det
    -0.06
    trx
    -0.06
     Hizmet
    -0.06
     Valley
    -0.06
    .cpu
    -0.06
     Documentary
    -0.06
     Liquid
    -0.06
    EndTime
    -0.06
    POSITIVE LOGITS
    ιας
    0.07
     cuerpo
    0.07
    fst
    0.07
     natural
    0.07
    ROME
    0.07
     pueda
    0.06
    .scenes
    0.06
     recycling
    0.06
     هستند
    0.06
    奧
    0.06
    Act Density 0.011%

    No Known Activations