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

    Neuronpedia

    INDEX
    Explanations

    say 's' ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denounced
    -0.07
     swelling
    -0.06
     ה
    -0.06
    ogenesis
    -0.06
    Adapter
    -0.06
    .Game
    -0.06
    Planning
    -0.06
    Intro
    -0.06
    Customer
    -0.05
     selon
    -0.05
    POSITIVE LOGITS
     grey
    0.07
    /W
    0.07
     mirrored
    0.06
     situace
    0.06
     �
    0.06
    flower
    0.06
    سون
    0.06
     skuteč
    0.06
    macı
    0.06
     attenu
    0.06
    Act Density 0.012%

    No Known Activations