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

    Neuronpedia

    INDEX
    Explanations

    marketing audiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     görd
    -0.09
    Semaphore
    -0.09
     moto
    -0.09
     braid
    -0.09
     motocic
    -0.09
     ави
    -0.08
     ured
    -0.08
     görül
    -0.08
    .tile
    -0.08
     avion
    -0.08
    POSITIVE LOGITS
     (*.
    0.08
     siblings
    0.08
     생성
    0.07
     expands
    0.07
    (custom
    0.07
     offsets
    0.07
     risiko
    0.07
     embodiments
    0.07
    生成
    0.07
     automaticamente
    0.07
    Act Density 0.001%

    No Known Activations