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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tile
    -0.08
     Ge
    -0.08
     municipalities
    -0.07
     comunidades
    -0.07
    	container
    -0.07
     rpc
    -0.07
    _ge
    -0.07
     td
    -0.07
     clubes
    -0.07
     batching
    -0.07
    POSITIVE LOGITS
     primi
    0.08
    صبح
    0.08
    èlement
    0.08
    érience
    0.08
     أخذ
    0.08
     Hertz
    0.08
    خذ
    0.08
    avaş
    0.08
    brauch
    0.08
     Hebrews
    0.08
    Act Density 0.000%

    No Known Activations