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

    Neuronpedia

    INDEX
    Explanations

    Interleaving sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overturn
    -0.07
     bekommst
    -0.07
     forensic
    -0.07
    otrans
    -0.07
     Pierce
    -0.07
     fraud
    -0.07
     attack
    -0.07
    itled
    -0.07
     basin
    -0.07
     ফুল
    -0.07
    POSITIVE LOGITS
     Reihen
    0.10
     interm
    0.10
    混
    0.10
    排列
    0.10
     chronological
    0.10
     mixes
    0.10
     alternating
    0.10
     repetitions
    0.10
     shuffled
    0.10
     σειρά
    0.09
    Act Density 0.024%

    No Known Activations