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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications (DOIs)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "_"
    -0.06
     oleh
    -0.06
     fos
    -0.06
    trx
    -0.06
     Cave
    -0.06
     bag
    -0.06
     grid
    -0.06
     уж
    -0.06
     viability
    -0.06
     vibes
    -0.06
    POSITIVE LOGITS
    ihilation
    0.07
     raced
    0.06
     kromě
    0.06
     появи
    0.06
    .rstrip
    0.06
     //----------------
    0.06
    fruit
    0.06
    unload
    0.06
    да
    0.06
    fds
    0.06
    Act Density 0.004%

    No Known Activations