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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    simp
    -0.06
    yb
    -0.06
     Sac
    -0.06
    _sim
    -0.06
     нор
    -0.06
     セ
    -0.06
     kì
    -0.06
     Foley
    -0.06
    .SE
    -0.06
    POSITIVE LOGITS
     +↵
    0.07
    ochastic
    0.07
    ELL
    0.07
    agination
    0.07
     carts
    0.06
    ibo
    0.06
    navigate
    0.06
     prize
    0.06
    _bool
    0.06
     hell
    0.06
    Act Density 0.000%

    No Known Activations