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

    Neuronpedia

    INDEX
    Explanations

    applied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izz
    -0.06
     };
↵
    -0.06
     mA
    -0.06
     Велик
    -0.06
    スター
    -0.06
    .—
    -0.06
    ोध
    -0.06
      
    -0.06
    (fake
    -0.06
    noop
    -0.06
    POSITIVE LOGITS
     ceasefire
    0.07
    .getAmount
    0.07
    445
    0.06
     продукты
    0.06
    Named
    0.06
    sequently
    0.06
    voje
    0.06
     arrays
    0.06
     opinion
    0.06
     price
    0.06
    Act Density 0.417%

    No Known Activations