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

    Neuronpedia

    INDEX
    Explanations

    height width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    负担
    -0.09
     jitter
    -0.08
    慕
    -0.07
     tackle
    -0.07
     traveler
    -0.07
     staple
    -0.07
    �
    -0.07
    化进程
    -0.07
     journey
    -0.07
     Chronicle
    -0.07
    POSITIVE LOGITS
    ...↵
    0.08
     post
    0.08
    ref
    0.08
    ves
    0.07
    iej
    0.07
     primera
    0.07
     voluntarily
    0.07
    '"↵
    0.07
    arella
    0.07
     presidente
    0.07
    Act Density 0.016%

    No Known Activations