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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _todo
    -0.07
     إلا
    -0.06
    >You
    -0.06
    lém
    -0.06
    _dark
    -0.06
     Bau
    -0.06
    _bn
    -0.06
    OBJECT
    -0.06
    刑
    -0.06
     알
    -0.06
    POSITIVE LOGITS
     hay
    0.06
    ?,
    0.06
    zion
    0.06
    izando
    0.06
    .option
    0.06
    τουργ
    0.06
     combin
    0.06
    waters
    0.06
    itt
    0.06
     jsonObject
    0.06
    Act Density 0.000%

    No Known Activations