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

    Neuronpedia

    INDEX
    Explanations

    issues and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pathTemplates
    0.43
     onRequest
    0.41
    တ်
    0.38
    ,\
    0.38
    чеб
    0.37
    自动
    0.37
    下方
    0.37
     reclaimed
    0.37
    ঙ্গিক
    0.37
     conventionally
    0.37
    POSITIVE LOGITS
     lackluster
    0.47
     масштаб
    0.47
     demise
    0.46
     disparity
    0.45
     inequality
    0.44
     массив
    0.44
     impuestos
    0.43
     desigualdad
    0.43
     turmoil
    0.43
    ただし
    0.43
    Act Density 0.013%

    No Known Activations