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

    Neuronpedia

    INDEX
    Explanations

    things between other things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     공고
    -0.07
    .Order
    -0.07
     gw
    -0.06
     Beach
    -0.06
     mạnh
    -0.06
    จากการ
    -0.06
    IntPtr
    -0.06
    -O
    -0.06
    机械
    -0.06
    ้ำ
    -0.06
    POSITIVE LOGITS
     rod
    0.07
    /apps
    0.06
    ॉम
    0.06
    Degrees
    0.06
    段
    0.06
    vox
    0.06
    pla
    0.06
    ــ
    0.06
     CA
    0.06
     VAN
    0.06
    Act Density 0.027%

    No Known Activations