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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zig
    -0.08
    쫑
    -0.07
    heartbeat
    -0.07
    éd
    -0.07
    .wait
    -0.07
     Ż
    -0.07
     inund
    -0.07
     ומת
    -0.07
     grands
    -0.06
     vượt
    -0.06
    POSITIVE LOGITS
    _OUTPUT
    0.07
    BL
    0.07
    	config
    0.07
    BA
    0.07
     Changed
    0.07
    	remove
    0.06
    佘
    0.06
    FS
    0.06
    تنسي
    0.06
     WALL
    0.06
    Act Density 0.004%

    No Known Activations