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

    Neuronpedia

    INDEX
    Explanations

    housing projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ded
    -0.08
    azy
    -0.07
    izens
    -0.06
     ブ
    -0.06
     lei
    -0.06
    	fd
    -0.06
    	try
    -0.06
    }_{
    -0.06
    ─
    -0.06
     bom
    -0.06
    POSITIVE LOGITS
    šel
    0.07
    .Creator
    0.07
     گردد
    0.06
     artículo
    0.06
     qual
    0.06
     robber
    0.06
    .getExternal
    0.06
    альний
    0.06
    _FACTOR
    0.06
     состоит
    0.06
    Act Density 0.120%

    No Known Activations