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

    Neuronpedia

    INDEX
    Explanations

    constructive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poz
    -0.07
    ssp
    -0.06
    kses
    -0.06
    ється
    -0.06
     battleground
    -0.06
    よび
    -0.06
    viso
    -0.06
    .persistent
    -0.06
     oku
    -0.06
    .Panel
    -0.06
    POSITIVE LOGITS
    รรม
    0.08
    eres
    0.06
     المل
    0.06
    ธรรม
    0.06
     Ryu
    0.06
    得到
    0.06
     بهره
    0.06
    307
    0.06
     Enjoy
    0.06
     jungle
    0.06
    Act Density 0.004%

    No Known Activations