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
    Dia
    -0.06
    ้ใน
    -0.06
    anoi
    -0.06
     pois
    -0.06
     dân
    -0.06
    增加
    -0.06
     MDB
    -0.06
     weaknesses
    -0.06
     diren
    -0.06
     eros
    -0.06
    POSITIVE LOGITS
    費
    0.07
     disclosure
    0.07
     Band
    0.07
    jing
    0.06
     Phòng
    0.06
    -exclusive
    0.06
                            ↵
    0.06
    revolution
    0.06
     apparatus
    0.06
    already
    0.06
    Act Density 0.000%

    No Known Activations