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

    Neuronpedia

    INDEX
    Explanations

    255

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    „P
    -0.07
    Orth
    -0.06
     cyt
    -0.06
    icz
    -0.06
    pink
    -0.06
     зам
    -0.06
     خاطر
    -0.06
    '\
    -0.06
     ánh
    -0.06
    /span
    -0.06
    POSITIVE LOGITS
     perplex
    0.06
    elist
    0.06
     config
    0.06
     mines
    0.06
     derivation
    0.06
     tensors
    0.06
     conflicts
    0.06
     crafting
    0.06
     edilmiş
    0.06
     soph
    0.06
    Act Density 0.009%

    No Known Activations