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

    Neuronpedia

    INDEX
    Explanations

    Similarity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accessible
    -0.07
     benefici
    -0.07
     Gould
    -0.07
    =S
    -0.07
    aklı
    -0.06
     memorial
    -0.06
     Fried
    -0.06
     eig
    -0.06
     phase
    -0.06
    vard
    -0.06
    POSITIVE LOGITS
    .square
    0.07
    ♛
    0.07
    🎼
    0.07
    🥤
    0.07
    DX
    0.07
    ทราบ
    0.07
     START
    0.07
     Explosion
    0.07
    房企
    0.07
     eğlen
    0.07
    Act Density 0.024%

    No Known Activations